This article proposes an improved rank based regression estimator obtained by replacing the ordinary integer ranks in the Wilcoxon rank-score regression procedure with smoothed ranks derived from a smoothed empirical cumulative distribution function. The smoothed ranks are computed via a continuous, nondecreasing kernel distribution function H that provides a differentiable approximation to the classical indicator function used in standard rank regression. Substituting these smoothed ranks into the Wilcoxon score function yields a new estimator for the slope parameter(s) of the simple and multiple linear regression model. We show that the proposed estimator inherits the robustness properties of classical rank regression while providing improved efficiency under heavy tailed error distributions and better handling of tied observations. A Wald type hypothesis test for the regression coefficients is derived and its asymptotic normality is established. A Monte Carlo simulation study compares new estimator with the ordinary least-squares (OLS) estimator, the classical Wilcoxon rank regression estimator, and the Theil and Sen estimator under several error distributions including the normal, Laplace, Cauchy, and contaminated normal. The proposed estimator achieves relative efficiencies at or above those of classical rank regression uniformly across all scenarios considered, with notable gains in the presence of outliers and heavy-tailed errors.

We give a principled derivation of the Soft-Min-SNR weight of Crowson et al. (2024). The spread divergence of Zhang et al. (2018) convolves both compared distributions with a Gaussian kernel before taking the Kullback-Leibler (KL) divergence; applied to the per-sample local matched-Gaussian surrogate at each timestep, it yields the closed-form weight w(t,lambda) = sigma^2 / (sigma^2 + lambda). Three consequences follow. First, for variance-preserving schedules, w(t,lambda) equals a constant multiple of Soft-Min-SNR with gamma' = (1+lambda)/lambda, deriving a validated heuristic rather than introducing a new weight. Second, the same weight matches Min-SNR-gamma at leading order under gamma approximately 1/lambda, giving a cross-walk between the soft and hard reweighting families. Third, a local-geometry analysis scales an SGD-difficulty proxy by w^3 at high-SNR timesteps. Complementary to the objective-level account of Kingma & Gao (2023), who unified monotonic-in-log-SNR weightings as ELBOs of noise-augmented data, ours smooths both compared distributions rather than only the data side. Empirically, the matching rule holds on CIFAR-10 (linear and cosine) and CelebA-64 (cosine), with trajectory-wide confirmation on the cross-dataset cut: |Ours - Min-SNR| averages 0.45 FID across seven intermediate checkpoints on the seed-42 CelebA-64 trajectory, roughly 3x tighter than either reweighter's gap to DDPM. The local-geometry prediction is partially borne out: Ours converges about 21% earlier than DDPM at mid-training FID thresholds on CIFAR-10's linear schedule, where high-SNR damping headroom is largest, but this iteration-efficiency advantage does not transfer to cosine or CelebA-64, where all three methods reach similar final FIDs. Overall: final-FID parity with dataset-dependent iteration efficiency, plus a principled matching rule across the Min-SNR family.

We study robust parameter estimation in sinusoidal regression models within a least absolute deviations (LAD) framework. While classical approaches rely predominantly on least-squares formulations, they are known to be sensitive to heavy-tailed noise and outliers. We formulate the estimation problem as direct minimization of the LAD objective and propose a simple, modular coordinate descent algorithm that exploits the partial convexity of the objective: amplitude parameters are updated via weighted median computations, leading to substantial computational improvements over traditional simplex-based optimization methods, while frequency parameters are estimated via a periodogram-inspired grid search with local refinement. We establish strong consistency and asymptotic normality of the proposed estimator under mild regularity conditions. Empirically, we demonstrate the method's effectiveness on both synthetic datasets and real-world time series, including the Mauna Loa atmospheric CO2 data, air passenger data, and UK drivers' deaths data, where robustness to non-Gaussian noise is essential. The proposed approach provides a simple, interpretable, and robust alternative to least-squares-based methods for sinusoidal signal estimation.

The monomial parameterization of finite-memory Volterra identification is ill-conditioned under non-Gaussian input, and the Wiener--Hermite expansion removes this ill-conditioning only for Gaussian white-noise input. We construct the distribution-matched Volterra--Wiener--Kunchenko (VWK) basis by oriented Gram--Schmidt orthogonalization of monomials in $L^2(P)$ and use it as an arbitrary-polynomial-chaos coordinate system for finite-memory Volterra identification from data, following the generalized polynomial chaos of Xiu and Karniadakis (2002) and the data-driven arbitrary polynomial chaos of Oladyshkin and Nowak (2012). The basis itself is classical; the contribution is the Volterra-estimation reading. First, an order-2 misspecification-penalty theorem shows that a self-normalized diagonal estimator in the variance-matched Gaussian basis incurs an excess $L^2(P)$ risk governed by the skew coefficient $δ=μ_3/σ^2$, vanishing exactly for symmetric inputs. Second, conditioning experiments separate the constructional fact that the population matched Gram is the identity from the finite-sample design Gram: at $n=2000$, the centered-exponential empirical VWK Gram remains far better conditioned than the power Gram, although it degrades with degree. Third, a machine-checked Lean 4 proof establishes the Binomial$(N,p)$ Krawtchouk row for arbitrary $N$. Full least squares over a fixed span is basis-invariant, so VWK stabilizes diagonal cross-correlation and regularized coordinate fits rather than claiming universal prediction superiority. The analysis is moment-based, finite-memory, and restricted to product input laws.

A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance. However, beyond simple cases such as conditional sampling, the target distribution is often left implicit, defined only through a sampling rule or a heuristic energy function. To address this, we propose Jeffrey guidance, a principled framework that extends diffusion-model control to applications beyond what standard guidance can express. It leverages Jeffrey's rule of conditioning to update marginal distributions towards a prescribed target, preserving the conditional structure and minimally perturbing the joint distribution. We first demonstrate Jeffrey guidance by targeting a prescribed embedding distribution. With Inception embeddings as the target, this leads to substantial reductions in FID on both CIFAR-10 and FFHQ. We further apply Jeffrey guidance to fairness on CelebA-HQ, updating an unconditional diffusion model to enforce independence between attributes.

We study the large sample asymptotic behaviour of the Maximum Likelihood Estimator of the discount and strength parameters $(α,θ)$ in the Ewens--Pitman model for random partitions, under mild assumptions on the data-generating mechanism. We show that four distinct regimes arise, depending on the limiting behaviour of the frequency spectrum. In particular, in contrast with previous work, we find that $θ$ may play a crucial role asymptotically. We further show that the existing literature implicitly focuses on only two of these regimes, and we relate this restriction to the constraints imposed by infinite exchangeability. Under the latter, indeed, the number of distinct blocks and the frequency spectrum are necessarily tied by a rigid structural relation. We prove that this lack of flexibility can be overcome through what we call the scaled Ewens--Pitman model, in which $θ$ is allowed to grow with the sample size $n$. Finally, we provide empirical evidence from real-world data showing that such extensions are needed to capture frequency spectra that fall outside the classical Ewens--Pitman framework.

We argue that dependent versions of McDiarmid's inequality are a useful but underutilized tool in mathematical statistics, learning theory and theoretical computer science. To make this point, we first highlight that approximate tensorization of entropy (ATE) implies McDiarmid's via the Entropy Method. Second, we derive McDiarmid's inequality for non-isotropic Gaussian random vectors $X \sim \mathcal N(μ, Σ)$ through ATE with a constant of the order of the condition number of $Σ$. We both independently obtain this ATE through a simple application of stochastic localization and also discuss how a more general ATE for the Gibbs sampler due to Ascolani et al., 2026 generalizes McDiarmid's-like concentration to strongly log-concave and log-smooth probability measures. We then apply the resulting concentration inequalities to resolve a question on the concentration of $\operatorname{sign}(X)$ posed by Simone Bombari, investigate Erdős-Rényi graphs under dependence and prove a Dvoretzky-Kiefer-Wolfowitz-type inequality for observations from a joint measure fulfilling ATE and continuous marginal CDFs. For the class of strongly log-concave and log-smooth measures, this result improves upon a prior Dvoretzky-Kiefer-Wolfowitz-type inequality for non-i.i.d. observations due to Bobkov and Götze, 2010, by establishing the expected $1/\sqrt{n}$-rate of convergence under weak dependence instead of $n^{-1/3}$.

This paper develops asymptotic theory for quantile estimation via stochastic gradient descent (SGD) with a constant learning rate. The quantile loss function is neither smooth nor strongly convex. Beyond conventional perspectives and techniques, we view quantile SGD iteration as an irreducible, periodic, and positive recurrent Markov chain, which cyclically converges to its unique stationary distribution regardless of the arbitrarily fixed initialization. To derive the exact form of the stationary distribution, we analyze the structure of its characteristic function by exploiting the stationary equation. We also derive tight bounds for its moment generating function (MGF) and tail probabilities. Synthesizing the aforementioned approaches, we prove that the centered and standardized stationary distribution converges to a Gaussian distribution as the learning rate $η\rightarrow0$. This finding provides the first central limit theorem (CLT)-type theoretical guarantees for the quantile SGD estimator with constant learning rates. We further propose a recursive algorithm to construct confidence intervals of the estimators with statistical guarantees. Numerical studies demonstrate the effective finite-sample performance of the online estimator and inference procedure. The theoretical tools developed in this study are of independent interest for investigating general SGD algorithms formulated as Markov chains, particularly in non-strongly convex and non-smooth settings.

Multiple testing adjustments, such as the Benjamini & Hochberg (1995) step-up procedure for controlling the false discovery rate (FDR), are typically applied to families of tests that control significance level in the classical sense: for each individual test, the probability of false rejection is no greater than the nominal level. In this paper, we consider tests that satisfy only a weaker notion of significance level control, in which the probability of false rejection need only be controlled on average over the hypotheses. We find that the Benjamini & Hochberg (1995) step-up procedure still controls FDR in the asymptotic regime with many weakly dependent p-values and an increasing number of rejections, and that certain adjustments for dependent p-values such as the Benjamini & Yekutieli (2001) procedure continue to yield FDR control in finite samples. Our results open the door to FDR controlling procedures in nonparametric and high dimensional settings where weakening the notion of inference may allow for power improvements.

This paper studies the hypothesis testing problem of deciding whether $m \geq 2$ complete weighted graphs with Gaussian edge weights are mutually correlated after unknown relabelings of their vertices. Under the null model all edge weights are independent standard Gaussians, whereas under the planted model the graphs share a latent vertex alignment and each pair of corresponding edge weights has correlation $ρ$. For fixed $m$, we identify the sharp information-theoretic threshold for detection. Above the threshold, a generalized likelihood-ratio test achieves strong detection, whereas even weak detection is impossible below the threshold. The result extends the two-graph detection threshold of Wu, Xu, and Yu to any fixed number of graphs, exhibits a side-information regime in which two graphs alone are insufficient but multiple graphs enable detection, and, together with the recovery threshold of Vassaux and Massoulié, shows that this Gaussian multi-graph model has no detection--recovery gap.

Recurrent event data frequently arise in biomedical studies, where individuals may experience multiple recurrences of the same type of events, such as recurrent hospitalizations. This article introduces a nonparametric method for recurrent events under a Bayesian ensemble learning framework, called Soft Bayesian Additive Regression Trees (SBART), which combines multiple soft decision trees to achieve high predictive accuracy and a smooth estimator of the underlying intensity of the recurrent events. The proposed model represents the conditional intensity function of the non-homogeneous Poisson process as the product of a time-constant baseline, a subject-specific frailty random effect, and a nonparametric component capturing potentially nonlinear covariate effects and unknown interactions among covariates and time. A two-layer data augmentation scheme is employed to efficiently incorporate the SBART component within our computational algorithm. Simulation studies demonstrate that our method, called RecSBART in short, achieves superior accuracy in estimating cumulative intensity compared to existing approaches, even when our modeling assumptions are not true. With the Bayesian analysis of a study of recurrent hospitalizations of colorectal cancer patients, we further demonstrate our RecSBART method's ability to reveal and interpret the underlying complex relationships among covariates in a recurrent events study.

Online conformal prediction must balance fast adaptation to distribution shift against stable coverage: feedback-driven methods react quickly but become volatile, while strongly discounted Bayesian methods lag and inflate intervals at tight coverage. We introduce \textbf{State-Adaptive Bayesian Conformal Prediction (SA-BCP)}, which forms the predictive quantile as a gated convex combination of long-term temporal inertia and local spatial evidence from a kernel density estimate, controlled by a single interpretable evidence threshold $K$. We establish three results: (i) asymptotic marginal validity of the resulting intervals; (ii) a closed-form expression for the MSE-optimal threshold, $K^*_{\mathrm{MSE}}=α(1-α)/M^{\mathcal{T}}$, trading the coverage-indicator (Bernoulli) variance against the temporal structural bias $M^{\mathcal{T}}$; and (iii) a rolling-origin procedure for selecting $K$ online -- consistent under stationarity, with $O(\sqrt{T\log N})$ regret against the best fixed $K$ and, for a segmented variant, a sublinear dynamic-regret bound under bounded drift. Across four financial-volatility and weather datasets, three target coverage levels, and eight baselines (including the strongest recent conditional-quantile methods, SPCI and KOWCPI), SA-BCP attains at-or-above-nominal coverage in most settings while producing substantially sharper intervals -- up to roughly $3\times$ lower Winkler score than discounted Bayesian CP at the tightest coverage -- and a coverage-matched audit confirms these efficiency gains are not an artifact of under-coverage. We disclose one principal limitation: a volatility-specialized conformal-GARCH competitor remains more efficient on its home volatility-base series, though it does not transfer across domains.

High-dimensional, underdetermined and highly correlated systems are common in data science practice, especially when analyzing physical measurements. In such settings, feature selection poses a fundamental challenge because multiple distinct sparse subsets may explain the response equally well. Their identification is crucial not only for predictive modeling but also for generating domain-specific insights into the underlying mechanisms. Yet, conventional methods typically isolate a single solution, obscuring the full spectrum of plausible explanations. This work introduces GEMSS (Gaussian Ensemble for Multiple Sparse Solutions), a variational algorithm designed to simultaneously discover multiple, diverse sparse feature combinations. The method employs a structured spike-and-slab prior for sparsity, a mixture of Gaussians to approximate the intractable multimodal posterior, and a Jaccard-based penalty to further control solution diversity. A single objective function is optimized via stochastic gradient descent. The method is tested on 128 comprehensive experiments by a novel benchmarking framework designed to generate artificial problems with multiple sparse solutions of equal predictive properties. This allows us to measure the retrieval of ground truth features rather than only evaluating predictive performance -- characteristics more fitting to our practical needs. A comparative analysis shows that GEMSS consistently outperforms five prominent feature selection methods adapted through the ALFESE framework. Finally, we demonstrate practical usability through 3 challenging real-world datasets from metabolomics and physical chemistry: GEMSS successfully isolates multiple distinct yet quality solutions. GEMSS is available as a PyPI package 'gemss'. The corresponding repository github.com/kat-er-ina/gemss/ includes the full codebase and a free, no-code application GEMSS Explorer.

Online joint estimation of a dynamical model's unknown parameters and states with uncertainty quantification is crucial in many applications. For example, digital twins dynamically update their knowledge of model parameters and states to support prediction and decision-making. Reliability and computational speed are vital for DTs. Online parameter-state estimation ensures computational efficiency, while uncertainty quantification is essential for making reliable predictions and decisions. In parameter-state estimation, the joint distribution of the state and model parameters conditioned on the data, termed the joint posterior, provides accurate uncertainty quantification. Because the joint posterior is generally intractable to compute, this paper presents an online variational inference framework to compute its approximation at each time step. The approximation is factorized into a marginal distribution over the model parameters and a state distribution conditioned on the parameters. This factorization enables recursive updates through a two-stage procedure: first, the parameter posterior is approximated via variational inference; second, the state distribution conditioned on the parameters is computed using Gaussian filtering based on the approximate parameter posterior. The algorithmic design is supported by a theorem establishing upper bounds on the joint posterior approximation error. Numerical experiments demonstrate that the proposed method (i) accurately infers both unobserved states and unknown parameters of dynamical and observation models; (ii) remains robust under noisy, partial observations and model discrepancies in a chaotic Lorenz'96 system; and (iii) scales effectively to a high-dimensional state-space system arising from the spatial discretization of a convection-diffusion equation. outperforming the joint ensemble Kalman filter in this setting.

Nonparanormal models describe the joint distribution of multivariate responses via latent Gaussian, and thus parametric, copulae while allowing flexible nonparametric marginals. Some aspects of such distributions, for example conditional independence, are formulated parametrically. Other features, such as marginal distributions, can be formulated non- or semiparametrically. Such models are attractive when multivariate normality is questionable but interpretability paramount. Most estimation procedures perform two steps, first estimating the nonparametric part. The copula parameters come second, treating the marginal estimates as known. This is sufficient for some applications. For other applications, e.g. when a semiparametric margin features parameters of interest or when standard errors are important, a simultaneous estimation of all parameters might be more advantageous. We present suitable parameterisations of nonparanormal models, possibly including semiparametric effects, and define four novel nonparanormal log-likelihood functions. In general, the corresponding one-step optimisation problems are shown to be non-convex. In some cases, however, biconvex problems emerge. Several convex approximations are discussed. From a low-level computational point of view, the core contribution is the score function for multivariate normal log-probabilities computed via Genz procedure. As a demonstration for the versatility of the theoretical and computational framework, we present a series of nonparanormal models for transformation discriminant analysis when some biomarkers are subject to limit-of-detection problems. Possible empirical gains of full maximum likelihood estimation compared to two-step approaches are illustrated in a simulation study targeting semiparametric efficient polychoric correlation analysis where a theoretical benchmark is available.

The Poisson compound decision problem is a long-standing problem is statistics, for which empirical Bayes methods are commonly used to estimate Poisson means in static or batch settings. We consider this problem in a streaming, or online, framework. Building on a quasi-Bayesian approach based on Newton's algorithm, we develop a sequential estimate that is easy to evaluate, computationally efficient, and has constant per-observation cost as the data accrue. We establish frequentist guarantees for the proposed estimate, including consistency and asymptotic optimality, with optimality understood as vanishing excess Bayes risk, or regret. Empirical performance is assessed through simulation studies and comparisons with benchmark procedures.

Small randomized controlled trials are often used to screen interventions before running larger follow-up studies. This is a critical phase of experimentation, as missing effective interventions or scaling up harmful ones can be very costly. A common proposal to mitigate these errors is to recruit samples that are representative of the target population, but this is often challenging in resource-constrained pilots. We challenge the narrative that representative samples are always superior by showing that when statistical significance testing determines whether interventions receive further study, the pilot trial composition that maximizes the downstream expected improvement in outcomes depends critically on its budget size. In the large-budget limit, the optimal pilot design converges to a sample that is representative of the target population. However, in the small-budget regime, the pilot designer maximizes expected impact by sampling only from a single homogeneous sub-population, chosen in a manner that depends on sampling costs and the designer's prior beliefs about heterogeneous treatment effects. Our proof of the small-budget result applies more generally when an RCT and significance test are used to decide whether to receive any non-adaptive downstream payoff, a result that may be applicable to other settings with constrained experimentation budgets.

Cluster randomized trials (CRTs) are frequently used to evaluate interventions, yet conducting causal mediation analysis in these settings remains challenging, particularly when the mediator is measured at the cluster level and the number of clusters is small. Standard inference methods often rely on asymptotic assumptions that fail in finite-sample settings, leading to biased variance estimation and invalid confidence intervals. In this paper, we propose a robust inference framework for causal mediation analysis in CRTs. We utilize parametric Bayesian models for the outcome and mediator to ensure computational efficiency and interpretability. Crucially, to quantify uncertainty, we specify a novel similarity-weighted Bayesian bootstrap (SWBB) with a `distance' metric between clusters; this avoids the need for restrictive parametric assumptions and allows the model to borrow more information from `closer' clusters. By combining observed data models with causal assumptions, our approach accurately estimates natural direct and indirect effects even with limited clusters. Simulation studies demonstrate that our method achieves nominal coverage probability across diverse scenarios. We illustrate the practical utility of our approach by assessing mediation in a CRT in Kenya.

Causal discovery aims to identify causal relationships among variables from observational or interventional data, typically represented by a directed acyclic graph (DAG). The causal invariance principle enables the identification of the causal parents of target variables by exploiting the stability of causal effects across different experimental settings. When some parents are unobserved, however, the induced graph over the observed variables may no longer be a DAG, and it may not be unique, complicating causal inference. For relevant configurations of latent parents, we characterize the induced graph and formalize the conditions under which causal invariance is preserved for the identification of the observed parents. Necessary and sufficient conditions for testing such invariance are formally established for a multivariate Gaussian target.

Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on. Recent work in causality-based domain generalization has shown how shared causal structure between domains can induce invariant predictors, e.g., models on a subset of features which have stable risk across structured domain shifts. However, the extent to which such population-level causal invariances can lead to gains in finite-sample settings remains underexplored. In particular, in practice we often have access to a few labeled target samples, a setting called supervised domain adaptation (sDA). In this paper, we explore when (full or partial) causal knowledge can provably improve supervised domain adaptation. As a first step, we study linear regression, where full or partial causal knowledge specifies a collection of invariant or possibly invariant feature subsets, each yielding a source-trained candidate predictor. We derive matching upper and lower bounds showing that finite-sample gains are governed by the target-risk margins separating the candidates, together with the finite-source estimation error. When these margins are sufficiently large relative to $n_Q$, an adaptive aggregation procedure can match the best candidate predictor while avoiding negative transfer relative to target-only learning. On the other hand, when the margins are too small, no algorithm can reliably exploit the candidate collection to obtain faster finite-sample rates. We further connect these margins to structural shift magnitude in linear SCMs and validate the theory on real-world causal benchmarks.

This study investigates semiparametric efficient estimation of causal and structural parameters in a semi-supervised setting. In our setting, unlabeled auxiliary regressors are available in addition to labeled observations consisting of outcomes and regressors. Our goal is to construct estimators of causal and structural parameters whose asymptotic variances are smaller than those of estimators constructed using only labeled data. We refer to this framework as prediction-powered causal inference (PPCI). We first derive the efficient influence function and the efficiency bound, which imply that the use of auxiliary regressors can attain a smaller asymptotic variance than the efficiency bound attainable from labeled observations alone. Then, by combining the efficient influence function with the debiased machine learning (DML) framework, we propose methods that we call DML-PPCI. If we construct an estimating-equation estimator, we refer to the method as EE-DML-PPCI; if we construct a targeted-learning estimator, we refer to the method as TMLE-DML-PPCI. The asymptotic variances of both estimators match our derived efficiency bound. In the construction of the estimators, estimation of the efficient influence function plays an important role. In our study, the efficient influence function is also a Neyman orthogonal score, which depends on the Riesz representer and the regression function. For Riesz representer estimation, we develop semi-supervised generalized Riesz regression with convergence rate guarantees.

Two-sample testing is a fundamental tool for detecting distributional differences across scientific domains, but classical tests (including kernel-based tests) can be ineffective on high-dimensional structured data such as images. Recent deep two-sample tests improve sensitivity in these settings by learning informative representations, yet they provide limited insight into which data features drive rejection of the null hypothesis $H_0$. To address this issue, we propose a counterfactual explanation framework for deep two-sample testing that generates sample-level edits moving observations from a source group toward a target group while explicitly reducing the discrepancy measured by the test. Our method combines a diffusion autoencoder with a pretrained deep two-sample test model and optimizes a maximum mean discrepancy (MMD) objective in the test model's representation space to produce plausible counterfactuals. We quantify distribution-level effects through changes in the test statistic and the resulting two-sample p-values. We evaluate the method on synthetic 2D shape datasets and two MRI cohorts. Across both settings, the counterfactual transformations consistently increase p-values relative to the original samples, indicating that the edited source set becomes statistically closer to the target distribution under the test. We measure minimality using LPIPS to ensure the counterfactuals remain close to the original samples. The resulting edits provide interpretable evidence of the features associated with the detected group differences. On MRI, the localized changes are consistent with known anatomical differences between cohorts.

Causal mediation analysis decomposes the total treatment effect into a portion operating through a hypothesized mediator and a residual direct portion. Identification of natural direct and indirect effects typically rests on the mediator stage of sequential ignorability, which cannot be empirically verified and requires explicit sensitivity analysis. We formulate the \emph{bridge score}, a mediator-stage balancing score, as a low-dimensional vector formed from the two treatment-specific mediator densities at a common mediator value, and show that it balances baseline covariates for the mediator stage relevant to natural effect identification. Conditional on the bridge score, we derive a sharp pointwise variance envelope on the unidentified mediator-outcome confounding function in terms of latent outcome relevance and residual selection. To make the bound operational for sensitivity analysis, we further introduce a residual budget calibration approach based on local residual outcome variation and record a complementary range bound for support-based restrictions. Finally, we show how the pointwise bound can be operationalized for inference through a scalar functional reduction and a Bayesian g-computation algorithm that combines observed-data posterior uncertainty with user-specified sensitivity uncertainty, rather than treating the unidentified sensitivity corrections as learned from the likelihood.

Evaluating the causal health effects of multivariate, continuous exposures, such as air pollution mixtures, is a critical public health challenge. A primary obstacle is the frequent violation of the positivity assumption, which renders the effects of standard deterministic interventions unidentified or heavily reliant on unreliable model extrapolation. In this paper, we develop a novel causal inference framework to address this challenge. We extend exponential tilting to multivariate exposures and address the critical question of how to compare different intervention directions fairly. This establishes a systematic framework for defining and evaluating various policy-relevant causal estimands, allowing researchers to address diverse scientific questions. We develop numerous methodological advancements, including efficient one-step estimation strategies, a Riemannian BFGS algorithm to solve a constrained manifold optimization problem, semiparametric efficiency bounds for causal estimands, minimax rates for estimators, and establishing asymptotic normality. We demonstrate our framework's utility by applying it to a nationwide environmental health dataset to identify the optimal strategy for reducing adverse health outcomes associated with a PM$_{2.5}$ chemical mixture.

In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence (GenAI). Specifically, we propose to use a deep generative model such as large language models (LLMs) to efficiently generate treatments and use their internal representation for subsequent causal effect estimation. We show that the knowledge of this true internal representation helps disentangle the treatment features of interest, such as specific sentiments and certain topics, from other possibly unknown confounding features. Unlike existing methods, the proposed GenAI-Powered Inference (GPI) methodology eliminates the need to learn causal representation from the data, and hence produces more accurate and efficient estimates. We formally establish the conditions required for the nonparametric identification of the average treatment effect, propose an estimation strategy that avoids the violation of the overlap assumption, and derive the asymptotic properties of the proposed estimator through the application of double machine learning. Finally, using an instrumental variables approach, we extend the proposed GPI methodology to the settings in which the treatment feature is based on human perception. The GPI is also applicable to text reuse where an LLM is used to regenerate existing texts. We conduct simulation and empirical studies, using the generated text data from an open-source LLM, Llama 3, to illustrate the advantages of our estimator over state-of-the-art causal representation learning algorithms.

This paper studies a two-stage model of experimentation, where the researcher first samples representative experimental participants from an eligible pool, then assigns each sampled unit to treatment or control, using matched $k$-tuples randomization at both stages. To implement such designs, we develop a fast new algorithm for matching units into $k$-tuples for any $k \ge 2$ and any dimension of covariates. By surveying 200 recent experimental working papers, we estimate that our algorithm newly enables multivariate fine stratification with provable match quality guarantees for about 44\% of experiments in economics. We show that finely stratified sampling and assignment both nonparametrically reduce the variance of treatment effect estimation, with the gains from stratified sampling increasing in the size of the eligible pool and how well covariates predict treatment effect heterogeneity. We develop new inference methods that fully exploit the efficiency gains from both design stages, allowing researchers to report smaller standard errors if they designed a representative experiment. An application to nine published experiments quantifies the efficiency gains.

We study the problem of diffusion parameter estimation for stochastic differential equation (SDE) models in scenarios where data and model are compatible only on specific scales that have yet to be determined. We introduce a simple and efficient method for selecting suitable rates at which given time series data should be subsampled in order to ensure that the statistical structure of the subsampled data is consistent with the behavior of the SDE model on an infinitesimal scale. Our approach is based on analyzing the statistics of the lengths of monotonically increasing or decreasing segments in the subsampled data sequence, which we refer to as monotone runs. As an analytical foundation, we prove for a large class of SDEs with additive noise that the lengths of monotone runs at an infinitesimal scale are approximately geometrically distributed with success probability $1/2$. This universal characterization is employed to derive an automated method for selecting appropriate subsampling rates for given time series data that is directly applicable in real-world scenarios and does not rely on an asymptotic framework of multiscale diffusions. The approach is demonstrated using an application from industrial mathematics concerning surrogate models for fiber lay-down curves in production processes of nonwoven textiles.

Here we address the problem of estimating the dimensionality and nature of parametric variation in an unknown generative process directly from time-series data, without specifying or fitting a model. In particular we suppose that inter-instance variation in collections of time series is caused by parametric variation in the generating model. We hypothesize that, given a sufficiently large library of time-series features, low-dimensional parametric variation will manifest as low-dimensional structure in feature space, enabling interpretable estimators of the underlying degrees of freedom to be constructed. We test our hypothesis using a library of over 7000 diverse and interpretable time-series statistics and thirteen simulated systems with known parametric variation, spanning linear stochastic processes, nonlinear oscillators, and chaotic dynamics. Our unsupervised, data-driven approach often reconstructs the underlying parametric variation across this extensive range of simulated dynamical systems while also yielding interpretable estimators for each underlying dimension. Applied to the movement dynamics of 1143 fruit flies, we use this method to extract biologically meaningful components corresponding to sex and circadian rhythmicity. Our results pave the way for much-needed data-driven methods to bridge the gap between interpretable theoretical understanding of dynamics and the large and complex datasets that characterize modern scientific problems.

Vine copulas provide a flexible framework for modeling complex multivariate dependence structures using only bivariate building blocks. Their practical success relies heavily on the simplifying assumption, which restricts conditional pair copulas to be independent of the specific conditioning values. While this assumption greatly facilitates estimation, it may lead to model misspecification in applications with pronounced varying conditional dependence. We propose a novel calibration strategy for simplified vine copula models based on observation-specific correction factors. These factors are derived using noise contrastive estimation (NCE), a supervised learning technique for density estimation that reframes the problem as a binary classification task with an easily sampled noise distribution. Treating the fitted simplified vine copula as the noise model, the NCE approach yields corrected log-likelihood estimates for individual observations, thereby locally adjusting the simplified vine toward the underlying data-generating dependence structure. Simulation studies demonstrate that the proposed calibration provides sensible and effective adjustments, improving model accuracy when the simplifying assumption is violated while remaining neutral when the simplified model is adequate. Two real-data applications further illustrate the practical benefits of the method. The results highlight NCE-based calibration as a promising tool to enhance simplified vine copula models without abandoning their computational tractability.

Gaussian processes are widely used for surrogate modeling in computer experiments, which often produce numerous intermediate variables that are not explicitly used in standard calibration frameworks. Calibration of imperfect models can be challenging without leveraging these variables, while fitting the emulator and the discrepancy models separately also poses identifiability issues. In this work, we propose a robust Gaussian process calibration framework that leverages intermediate variables for discrepancy modeling. The framework integrates a structured intermediate variable selection process, a discretized scaled Gaussian stochastic process (S-GaSP) to constrain the discrepancy term, and a space-filling design strategy for selecting constraint points. This enables joint modeling of the emulator and discrepancy, improving predictive performance, providing principled uncertainty quantification, and alleviating identifiability risks. We demonstrate its efficacy on a nuclear physics application involving binding energies, where it outperforms baseline approaches.

We extend the Prais-Winsten AR(k) generalized least squares (GLS) transformation to panel data within the Beck-Katz panel-corrected standard error (PCSE) framework and implement the method in the community-contributed Stata package xtpraisk. As the panel extension of Prais-Winsten, xtpraisk is the natural comparator to xtscc, the panel extension of Newey-West and implementation of the Driscoll-Kraay estimator. We conduct a Monte Carlo simulation to validate the statistical properties of xtpraisk and compare its finite-sample performance with xtscc. The simulation spans autoregressive orders 1-3, three autocorrelation scenarios, three panel sizes, six series lengths, and five effect sizes, with 2,000 replications per condition. Across all conditions, xtpraisk achieved higher power than xtscc while maintaining near-nominal Type I error rates, confidence interval coverage, and standard error calibration. In contrast, xtscc exhibited systematic standard error underestimation and inflated Type I error at short series lengths, with both deficiencies worsening as autoregressive order increased. Both estimators were essentially unbiased. Misspecification of the autoregressive order did not degrade xtpraisk's inferential performance, and cross-panel correlation and panel size had negligible effects on the relative performance of either estimator. The results indicate that xtpraisk is preferable when both statistical efficiency and valid inference are priorities, particularly under persistent higher-order autocorrelation and short to moderate series lengths.

We introduce a switching Hamiltonian Monte Carlo method for sampling from finite mixture Boltzmann-Gibbs distributions. We propose symmetric numerical integrators to approximate switching Hamiltonian dynamics interlaced with Poisson jumps, where the regime-switching chain is simulated using the uniformization technique or the stochastic simulation algorithm. We prove geometric ergodicity of the resulting Markov chain. We develop an approach based on the discrete Poisson equation associated with numerical schemes to estimate the error in computing ergodic averages. Using this approach we prove that the proposed numerical integrators have second-order bias. This approach is simple and can be generalized to other settings, for example, kinetic Langevin equations. Finally, we verify the convergence result via numerical experiment.

We give a simple, unified, and nearly tight bound for sampling arbitrary logconcave distributions from a warm start using the In-and-Out algorithm along with exponential lifting. The main new ingredient in the analysis is an improved bound on the Poincaré constant of a lifted distribution. As a consequence, the resulting convergence rate is nearly tight for both constrained settings (e.g., Gaussian restricted to a convex body) and well-conditioned settings (e.g., strongly logconcave and smooth densities).

Forecasting the evolution of complex dynamical systems remains a fundamentally challenging task, primarily due to pronounced nonlinear interactions, high-dimensional state spaces, and the concomitant requirement for rigorous and reliable uncertainty quantification. Contemporary reduced-order modelling (ROM) frameworks frequently exhibit inherent trade-offs among predictive accuracy, numerical stability, and interpretability, and thus often fail to achieve an optimal balance among these competing objectives. To address these limitations, we propose a framework for forecasting complex dynamical systems via a kernel autonomous ordinary differential equation approach based on Gaussian Processes and Quadratic Order Model Reduction. Our base method, the Gaussian Process Ordinary Differential Equations model, allows accurate short-term forecasting with uncertainty quantification, and it provably converges to the real autonomous equation in the smooth case. We integrate it with quadratic order reduced-order modelling and sphere projection for learning the latent dynamics efficiently while preserving stability. Numerical experiments demonstrate that our full model outperforms ROM forecasting methods such as Extended Dynamic Mode Decomposition, Bagging Optimised Dynamic Mode Decomposition and Linear and Nonlinear Disambiguation Optimisation in terms of accuracy or computational costs. These results demonstrate the potential of the framework as a robust and stable tool for forecasting complex dynamical systems with rigorous uncertainty quantification.

Multidisciplinary design analysis of coupled engineering systems requires the computation of equilibrium states in which all disciplinary coupling variables are mutually consistent. Conventional fixed-point iteration resolves this consistency problem separately at each design point, which can become expensive when disciplinary evaluations are costly and many analyses are required in outer-loop tasks such as multidisciplinary design optimization, uncertainty quantification, or digital twin updating. This paper introduces REMAL, a residual manifold surrogate modeling framework for coupled systems. Instead of approximating each discipline independently or directly learning converged coupling variables, the proposed method learns a surrogate model of the joint residual manifold via multitask Gaussian process models. An entropy-based active learning strategy selects additional residual evaluations near uncertain zero-contour regions, and equilibrium states for new design inputs are recovered by solving a nonlinear least squares optimization problem using only the trained surrogate. The method is evaluated on four engineering coupled system benchmarks: a satellite model, an aerostructural model, a finite-element gas-turbine heat-transfer and economics model, and a modified turbine model with added feedback coupling. Across these cases, REMAL consistently demonstrates the cost effectiveness when repeated evaluations of the fixed point across the design space are necessary. Theoretically, we show that, under mild assumptions, REMAL's predictive fixed point error is bounded.

Langevin dynamics on Riemannian manifolds is analyzed. Conditions ensuring the existence of a suitable logarithmic Sobolev inequality (rapid mixing to the Gibbs measure) are identified. These conditions involve the curvature of the manifold, the inverse temperature, escaping directions from saddle points, and exclude barren plateaus and spurious local minima. We show that when these conditions are met, mixing times polynomial in the dimension of the manifold are achievable. This result is obtained through a relation between Langevin processes in the domain and in the image of a Riemannian submersion. Such a relation can be of independent interest.

Importance sampling is a Monte Carlo method which designs estimators of expectations under a target distribution using weighted samples from a proposal distribution. When the target distribution is complex, such as multimodal distributions in highdimensional spaces, the efficiency of importance sampling critically depends on the choice of the proposal distribution. In this paper, we propose a novel adaptive scheme for the construction of efficient proposal distributions. Our algorithm promotes efficient exploration of the target distribution by combining global sampling mechanisms with a delayed weighting procedure. The proposed weighting mechanism plays a key role by enabling rapid resampling in regions where the proposal distribution is poorly adapted to the target. Our sampling algorithm is shown to be geometrically convergent under mild assumptions and is illustrated through various numerical experiments.

The problem of optimising functions with intractable gradients frequently arises in machine learning and statistics, ranging from maximum marginal likelihood estimation procedures to fine-tuning of generative models. Stochastic approximation methods for this class of problems typically require inner sampling loops to obtain (biased) stochastic gradient estimates, which rapidly becomes computationally expensive. In this work, we develop sequential Monte Carlo (SMC) samplers for optimisation of functions with intractable gradients. Our approach replaces expensive inner sampling methods with efficient SMC approximations, which can result in significant computational gains. We establish convergence results for the basic recursions defined by our methodology which SMC samplers approximate. We demonstrate the effectiveness of our approach on the reward-tuning of energy-based models within various settings.

How can we learn the laws underlying the dynamics of stochastic systems when their trajectories are sampled sparsely in time? Existing methods either require temporally resolved high-frequency observations, or rely on geometric arguments that apply only to conservative systems, limiting the range of dynamics they can recover. Here, we present a new framework that reconciles these two perspectives by reformulating inference as a stochastic control problem. Our method uses geometry-driven path augmentation, guided by the geometry in the system's invariant density to reconstruct likely trajectories and infer the underlying dynamics without assuming specific parametric models. Applied to overdamped Langevin systems, our approach accurately recovers stochastic dynamics even from extremely undersampled data, outperforming existing methods in synthetic benchmarks. This work demonstrates the effectiveness of incorporating geometric inductive biases into stochastic system identification methods.

Plug-and-Play (PnP) algorithms are a class of iterative algorithms that address image inverse problems by combining a physical model and a deep neural network for regularization. Even if they produce impressive image restoration results, these algorithms rely on a non-standard use of a denoiser on images that are less and less noisy along the iterations, which contrasts with recent algorithms based on Diffusion Models (DM), where the denoiser is applied only on re-noised images. We propose a new PnP framework, called Stochastic deNOising REgularization (SNORE), which applies the denoiser only on images with noise of the adequate level. It is based on an explicit stochastic regularization, which leads to a stochastic gradient descent algorithm to solve ill-posed inverse problems. A convergence analysis of this algorithm and its annealing extension is provided. Experimentally, we prove that SNORE is competitive with respect to state-of-the-art methods on deblurring and inpainting tasks, both quantitatively and qualitatively.

We investigate the convergence properties of popular data-augmentation samplers for Baye\-sian probit regression. Leveraging recent results on Gibbs samplers for log-concave targets, we provide simple and explicit non-asymptotic bounds on the associated mixing times (in Kullback-Leibler divergence). The bounds depend explicitly on the design matrix and the prior precision, while they hold uniformly over the vector of responses. We specialize the results for different regimes of statistical interest, when both the number of data points $n$ and parameters $p$ are large: in particular we identify scenarios where the mixing times remain bounded as $n,p\to\infty$, and ones where they do not. The results are shown to be tight (in the worst case with respect to the responses) and provide guidance on choices of prior distributions that provably lead to fast mixing. An empirical analysis based on coupling techniques suggests that the bounds are effective in predicting practically observed behaviours.

Recent advances in time series anomaly detection (TSAD) have highlighted the effectiveness of self-supervised classification-based approaches. These methods apply transformations to normal training samples, training a classifier to recognize transformation-specific patterns that help identify anomalies through increased classification errors. Despite their strong performance, a significant challenge is their lack of explainability, as they provide limited insight into the characteristics of flagged anomalies. To address this limitation, we propose ProtoX-AD, a prototype-based self-explainable framework for self-supervised TSAD. ProtoX-AD learns transformation-aware latent representations alongside interpretable prototypes, enabling both accurate anomaly detection and the identification of distinct anomalous profiles through prototype-based explanations. Additionally, it allows for systematic analysis of how transformation design impacts detection performance and explainability. Experimental results on synthetic and real-world datasets demonstrate that ProtoX-AD achieves detection performance comparable to its black-box counterparts while offering more consistent and semantically meaningful explanations than existing explainable baselines. Our code is publicly available at https://github.com/Aitorzan3/ProtoX-AD.

We propose a robust feature-weighted jump model for time-dependent clustering. A penalty is used to encourage smoothness of transitions over time, while robustness is achieved through the use of a Tukey's biweight loss function. An additional parameter controls the variability of feature weights across states, allowing the model to assign state-specific relevance to each feature. We illustrate in simulation how the method accurately recovers the true cluster sequence and reliably identifies relevant features, outperforming competing approaches, particularly in the presence of outliers. We conclude with two empirical applications, one on the number of conflict-related homicides in Kosovo in the period 1998-2000, and another on macroeconomic performance of twelve European countries in the period 1949-2024.

Klindt, LeCun, and Balestriero (arXiv:2605.26379) proved that Joint-Embedding Predictive Architectures (JEPAs) achieve linear identifiability, the linear recovery of the world's true latent variables, if and only if the world's latent dynamics follow a Gaussian, stationary process. This Gaussian boundary implies a fundamental limit on temporal consistency: for any non-Gaussian physical system, the representation error of a statistical World Model grows monotonically with time. We prove that this limit is an artifact of the statistical alignment mechanism, not a property of World Models in general. We introduce the Physics-Grounded Symbolic Architecture (PGSA) and prove three results: (1) a PGSA achieves exact linear identifiability for all physical regimes, regardless of the latent distribution; (2) the per-step error of a PGSA is bounded by numerical precision alone; and (3) as a direct consequence, a PGSA maintains temporal consistency for an unbounded number of transitions, a property we term near-infinite temporal consistency. We further prove that statistical World Models cannot achieve this property for any non-Gaussian system, regardless of model capacity or the volume of training data. The algebraic cores of four of the theorems are formalized in Lean 4 with Mathlib4 v4.31.0 (zero sorry placeholders); the Klindt et al. converse is taken as an external premise. The contrast establishes that symbolic grounding in the causal generator of the world's dynamics is the sufficient condition and, in non-Gaussian regimes, the only condition for near-infinite temporal consistency.

Understanding the minimal assumptions necessary for generalization is the fundamental question in learning theory. Unfortunately, most results rely heavily on independence (or some proxy thereof) of the data-generating process, while results for strongly dependent data are far more limited. Towards addressing this gap, we introduce the framework of simulatable processes, where the learner has access to a simulator that approximates the distribution generating the data (which may be an arbitrarily complex and dependent process). Surprisingly, given access to such a simulator, we show that we can recover the same learning guarantees as in the classical setting with independent data, namely, error bounds that depend on the VC dimension. Further, we use this framework to study the power of conditional sampling and show strict statistical and computational advantages in this setting. As a highlight of our framework, we exhibit a single algorithm that simultaneously learns any given VC class under all processes samplable in bounded polynomial time, with regret controlled by the time-bounded Kolmogorov complexity of the process. This provides a significant conceptual broadening of the classical PAC model.

Speculative decoding speeds up LLM inference by using a draft model to generate tokens, with an acceptance-rejection scheme that ensures that the output matches the target distribution. Adapting this to continuous diffusions is difficult because speculative sampling requires drawing from a residual distribution. While straightforward in discrete spaces, efficiently sampling this residual in continuous space is non-trivial. Consequently, existing diffusion adaptations either use computationally inefficient sampling techniques or rely on an alternative scheme. In this work, we introduce a novel scheme that efficiently implements the original speculative sampling mechanism for diffusion models. Our approach offers a critical advantage over current methods: it enables us to adapt block verification from LLMs to diffusions -- which provably improves the acceptance rate of drafts. Furthermore, we formalize and analyze the Free Drafter, a heuristic self-speculative drafter for diffusions that requires no training. By enabling block verification, our Free Drafter yields up to a 6.3% speedup over existing speculative methods with no additional training and negligible overhead beyond the existing parallel verification pass.

Two dominant approaches have emerged for generating probabilistic forecasts of physical systems: generative models, such as diffusion or flow matching; and ensembles of deterministic models with stochasticity injected, trained using the continuous ranked probability score (CRPS) loss. While both approaches have demonstrated strong predictive accuracy, the reliability of their uncertainties has not been systematically assessed. We address this gap by developing a framework to evaluate both approaches across diverse 2D spatiotemporal physical systems, under matched model size and computational budget. We assess the reliability of probabilistic emulation by inspecting the empirical coverage of predictive intervals, while also considering accuracy and computational efficiency metrics. CRPS-trained ensembles typically achieve more reliable uncertainties on both single-step prediction and autoregressive rollouts, demonstrating better coverage than the standard alternative of training generative models in a latent space. Moreover, the CRPS approach offers significantly faster inference. When generative models are trained in ambient rather than a compressed latent space, which is often infeasible for high-dimensional problems, they exhibit comparable coverage to CRPS-trained ensembles, though with substantially larger inference latency. In contrast, when CRPS-trained ensembles are trained in latent space they do not show a marked degradation in coverage with respect to ambient space. Both generative models and CRPS-trained ensembles demonstrate good predictive accuracy. To facilitate future research and application, we release AutoCast, a modular framework implementing both generative models and CRPS-trained ensembles, alongside AutoSim, a flexible dataset generation package for rapid prototyping.

Physics-Informed Neural Networks (PINNs) are an attractive tool for partial-observation problems in biology, where the governing dynamics are known but some compartments cannot be measured. Chemotherapy pharmacokinetics (PK) is a clean instance: drug concentration in plasma is routinely measured, but concentration in tissue -- which determines tumour kill and off-target toxicity -- is not. We benchmark a PINN against the standard clinical baseline (nonlinear least-squares on the analytical biexponential plasma solution, hereafter NLS) and a physics-agnostic neural baseline (a data-only MLP) on two PK problems. On the linear two-compartment problem, NLS is near-optimal; the PINN matches it to within a small constant factor while also producing the tissue curve in a single training pass, whereas the data-only MLP fails on tissue by roughly 10x. On a Michaelis-Menten extension (saturable elimination), the biexponential closed form no longer exists, so NLS is mis-specified and silently returns meaningless rate constants. The PINN instead exposes a deeper fact: the Michaelis-Menten two-compartment model is non-identifiable from plasma alone, and the PINN reports this honestly by converging to a basin with k12 -> 0. Adding two sparse tissue observations largely resolves identifiability: across five seeds the PINN recovers k21 to within 1% of truth and Vmax, Km to within one standard-deviation bar, while k12 moves in the correct direction (0.02 -> 0.82) but remains ~2 sigma below truth -- a recovery the closed-form NLS estimator cannot attempt at all, because its biexponential ansatz describes only plasma. Our claim is not that PINNs beat NLS. It is that PINNs offer a uniform recipe that ties the textbook estimator on the textbook problem, exposes structural identifiability that the textbook estimator hides, and absorbs heterogeneous measurements within a single loss.

We give a short proof that the majority vote of three independent consistent classifiers is an optimal learner in the realizable PAC setting. This proves optimality for the simplest voting scheme, while simplifying both the algorithmic structure and the probabilistic analysis of previous voting learners, including the algorithm of S. Hanneke and the analysis of bagging by K. Green Larsen.

This paper studies a variation of the classic network alignment problem, named diffusion-network alignment. The goal is to align the vertices of a rooted diffusion tree to the vertices of a network, where the diffusion tree could be from a communication trace or contact tracing, and the network could be an online or offline social network. Different from the classic network alignment where both networks are fully observed, this model captures the information asymmetry of two networks. To solve this problem, this paper presents an efficient algorithm based on tree correlation tests to extract alignment information from local neighborhoods. We analyze the performance of the algorithm in the sparse graph regime and show that with high probability, all matched pairs are correct. Furthermore, for each vertex on the diffusion tree, this paper establishes an explicit lower bound on the probability that the vertex is correctly matched. These lower bounds are depth-dependent and increase as vertices get closer to the root.

Auto-regressive models have emerged as powerful tools for sequential data, from language to video. Understanding how and why these models learn latent representations remains an open theoretical question. In this work, we demonstrate that when trained by empirical risk minimization on data from partially observed linear dynamical systems, two-layer linear auto-regressive models naturally learn to approximate Kalman filtering. In particular, we show that the learned hidden representation coincides, up to a similarity transformation, with the state estimates produced by the optimal (Kalman) filter, even though the model has no explicit knowledge of the underlying dynamics or state. The result follows from three main insights. First, we establish that the Kalman filter is well approximated by an auto-regressive model with bounded truncation error. Second, we show that despite non-convexity, the two-layer optimization landscape is benign, i.e., all stationary points are either strict saddles or global minima. Finally, as our main contributions, we provide finite-sample guarantees on prediction error, parameter estimation error, and latent state recovery. Numerical simulations support the theoretical results and demonstrate that the latent representations of auto-regressive models recover state estimates.

The standard taxonomy of predictive uncertainty defines epistemic uncertainty as the part removable by collecting more data, while the standard measure identifies it with a mutual-information term. We prove the definition and the measure are extensionally inconsistent. On an explicit construction, the measure assigns all uncertainty to the epistemic class, yet no quantity of training data reduces it. Reducibility is instead a property of the pair (uncertainty, acquisition class), and the dichotomy resolves into three parts: aleatoric, sample-reducible epistemic, and mechanism-reducible epistemic uncertainty. An exact identity for the value of an observation shows that in-distribution data never reduces mechanism-irreducible uncertainty and generically increases it. Ensemble disagreement, the deployed epistemic estimate, tracks the training procedure rather than the epistemic term. It collapses to zero beneath a positive truth under consistent training, and equals hyperparameter-scaled initialization noise under interpolation. A finite-sample falsification test and seed-swept experiments confirm the theory.

Two-dimensional magnets offer compelling platforms for spintronics and quantum technologies, yet predicting their magnetic ground states, moments, and anisotropy remains challenging. This limitation primarily arises because existing machine-learning representations encode chemical environments without capturing the symmetry or exchange physics that govern magnetism. In this work, we introduce the symmetry-electronic fingerprint (SEF), a physically interpretable representation that encodes crystallographic symmetry operations, Wyckoff-site geometry, together with site-resolved electronic structure. Combined with ensemble learning with random forests, the SEF accurately classifies magnetic ordering while regressing moments alongside anisotropy energies while simultaneously resolving the distinct regimes of itinerant Stoner ferromagnetism from localized superexchange. What sets the SEF-trained models apart is that regions of elevated model uncertainty are not a failure but a diagnostic, identifying materials where these mechanisms compete. First-principles calculations on Co- and Ni-based halides and oxides confirm that these regions correspond to genuine near-degenerate FM and AFM phases with magnetic frustration, suppressed anisotropy, and emergent non-collinear ordering. By encoding symmetry together with exchange physics directly into the representation unlike conventional descriptors, the SEF transforms model uncertainty into a compass pointing toward two-dimensional materials where small perturbations drive transitions between collinear, frustrated, or non-collinear magnetic phases.

We investigate limitations of learning $\tanh$ neural networks from point evaluations under finite-precision computations and $L^p$ accuracy guarantees, building on Berner, Grohs, and Voigtländer (2023). Our approach is based on a novel construction of sharply localized bump functions via iterated $\tanh$ activations. Using this mechanism, we show that, in a finite-precision setting, no adaptive randomized algorithm based on $m$ samples can achieve a convergence rate higher than the Monte Carlo rate $O(m^{-1/p})$ in the $L^p$ norm, unless the sampling budget grows exponentially with the size of the network parameters and architecture. The results reveal fundamental limitations imposed by finite precision on the learnability of classes containing localized bump functions, extending previous results for ReLU networks to the $\tanh$ setting.

Neural ordinary differential equations (neural ODEs) have rapidly gained prominence as a powerful and unifying framework for conceptualizing artificial neural networks, elegantly connecting the continuous-time modeling of dynamical systems with the discrete, data-driven paradigm of modern deep learning. Beyond their practical advantages they offer fresh theoretical insights into the training and generalization properties of neural networks. The distinctive feature of this framework is its dual dynamical nature: inference dynamics, which govern the ODE evolution during forward computation, and training dynamics, which control the optimization of model parameters. This makes neural ODEs a particularly well-suited theoretical framework for studying a large variety of settings such as multi-layer neural networks (ResNets for example), autoregressive models (with next-token generation dynamics), generative models, and recurrent neural networks in theoretical neuroscience. In this work, we introduce a theoretically grounded class of models for studying neural ODEs trained via online stochastic gradient descent. We solve the training dynamics of these models via dynamical mean field theory and derive learning curves in the high-dimensional limit.

We apply the Weibull distribution -- a two-parameter family from extreme-value theory -- as a diagnostic framework for element-wise weight magnitude distributions in transformers. At initialization, i.i.d. Gaussian weights give |w| ~ HalfNormal, yielding k ~ 1.20 via middle-80% probability-plot fit (the protocol used throughout this work). This anchor makes k a principled, architecture-independent measuring stick for training dynamics; fitting each weight matrix independently at every layer at every checkpoint enables per-component, per-layer, and per-step diagnostics that aggregate statistics cannot resolve. Applying this framework to 12 model entries spanning 7 architectural families (Pythia, OLMo-1/2, LLaMA-3, Mistral, Qwen2.5/3) reveals three findings. First, FFN modules and the attention output projection W_o -- the Transmission Class -- fall in a narrow k band: median terminal k in [1.186, 1.204] across 12 entries (cross-family CV = 0.51%), shared across SwiGLU/GeLU activations, Pre-LN/QK-Norm placements, and 70M-14B sizes. Second, the attention input projections W_q, W_k -- the Selection Class -- depart from the Weibull family, with severity shaped by storage: separately-stored Q/K (OLMo-1, OLMo-2) yields k in [0.76, 0.99] (deep); GQA models yield k in [1.10, 1.16] (mild); Pythia's merged W_qkv occupies a transitional zone tracking training budget T/tau monotonically. Third, lambda grows substantially during training and scales with sqrt(eta/lambda_wd) within the Pythia family (Pearson r = 0.94, three Transmission kinds), directionally consistent with Fan et al. (2025). The two parameters carry independent information: k labels the functional class, lambda labels training progress. We release npm-weibull-py v0.4 (Python library) and DATABASE_v9_1 at https://github.com/tiexinding/NPM-Weibull-public .

Modeling unknown latent functions from finite, irregularly sampled measurements is a recurring challenge across science and engineering. Neural processes (NPs), a family of probabilistic functional models, are promising solutions -- especially when endowed with domain-specific symmetries like translation equivariance, which improve sample efficiency and generalization. Yet existing translation-equivariant NPs face two limitations: (i) they stack generic components with non-linearities, obscuring the induced function class and limiting interpretability; and (ii) convolutional designs rely on kernels with local receptive fields and require dense uniform input grids, while attention-based methods avoid these issues but scale quadratically with the number of observations. We address both with two contributions. First, using the Volterra expansion, we characterize continuous translation-equivariant operators as sums of higher-order convolutions, yielding analytical transparency while admitting efficient approximation by first-order convolutions. Second, we introduce set Fourier convolutions (SFConvs), a frequency-domain parameterization that operates directly on irregularly sampled points, achieves approximately global receptive fields, and scales linearly in the number of observations. Building on these ideas, we propose two conditional NPs (CNPs): SFConvCNPs, which stack SFConv blocks with non-linearities, and SFVConvCNPs, which integrate the Volterra formulation. Experiments on synthetic and real-world datasets demonstrate our methods' efficacy against state-of-the-art baselines.

Many problems in computational science and engineering become one-to-many after coarse graining, partial observation, or inverse reconstruction: a resolved state may not determine a unique subgrid forcing, a structural descriptor may not determine a unique effective response, and a low-resolution observation may correspond to many plausible high-resolution fields. In such settings, deterministic surrogates may learn a well-defined mathematical object while still missing application-relevant uncertainty. This tutorial develops a self-contained module centered on the conditional-mean barrier: the point at which a squared-loss predictor has reached the conditional mean and the remaining error is irreducible aleatoric variance. We give two diagnostics for locating this barrier, residual-feature orthogonality and the coefficient of determination against its explained-variance ceiling, and prove that adding latent randomness to a squared-loss predictor collapses it back to the conditional mean. Crossing the barrier therefore requires a loss that scores distributions rather than point predictions. We briefly organize common distributional objectives, including negative log-likelihood, moment and observable matching, variational objectives, adversarial divergences, and score matching, by the feature of the conditional law each targets. The emphasis is the boundary itself and a finite-data procedure for recognizing it, rather than a survey of methods beyond it. CPU-based demonstrations on a two-branch law and a two-scale Lorenz-96 closure problem show how the diagnostics distinguish deterministic underfitting from residual distributional variability.

Mirror Descent (MD) is a scalable first-order method widely used in large-scale optimization, with applications in image processing, policy optimization, and neural network training. This paper generalizes MD to optimization on Riemannian manifolds. In particular, we develop a Riemannian Mirror Descent (RMD) framework via reparameterization and further propose a stochastic variant of RMD. We also establish non-asymptotic convergence guarantees for both RMD and stochastic RMD. As an application to the Stiefel manifold, our RMD framework reduces to the Curvilinear Gradient Descent (CGD) method proposed in [26]. Moreover, when specializing the stochastic RMD framework to the Stiefel setting, we obtain a stochastic extension of CGD, which effectively addresses large-scale manifold optimization problems.

Evaluating and interpreting latent representations, such as variational autoencoders (VAEs), remains a significant challenge for diverse data types, especially when ground-truth generative factors are unknown. To address this, we unify several state-of-the-art disentangled VAE approaches for latent space disentanglement into one framework -- bfVAE. To assess the effectiveness of a disentangled VAE model and enhance latent space interpretability, we propose Feature Variance Heterogeneity via Latent Traversal (FVH-LT) and Dirty Block Sparse Regression in Latent Space (DBSR-LS). To ensure robust interpretability of learned latent space, we develop a greedy alignment strategy (GAS) that mitigates label switching and aligns latent dimensions across runs to set the foundation of result aggregation. We also introduce a convenient scalar latent space separation index (LSSI) based on the GAS-aligned outputs of FVH-LT and DBSR-LS to summarize the overall latent structural separation without knowledge of the ground-truth generative factors. We compare bfVAE to five VAE models and validate the effectiveness FVH-LT, DBSR-LS, and LSSI in on seven tabular and image datasets. Under our examined experimental settings, bfVAE provides a more flexible disentanglement framework achieves more favorable overall trade-off between disentanglement and reconstruction than the benchmark VAE models; FVH-LT and DBSR-LS reliably uncover semantically meaningful and domain-relevant latent structures and generally yield consistent results; and LSSI makes an effective quantitative summary of latent structural separation.

The RemOve-And-Retrain (ROAR) benchmark is widely used to evaluate feature attribution methods, yet its validity remains underexplored from an information-theoretic perspective. We show that model- and data-agnostic post-processing of attribution maps (transformations that, by the data processing inequality, \emph{cannot} add information about the decision function) can often improve ROAR scores. This means that an improved ROAR ranking is not, by itself, evidence that an attribution map carries more information about the model. We trace this failure mode to a bias toward spatially blurry masks. Experiments on CIFAR-10, SVHN, and CUB-200 show a consistent association between blurriness and ROAR performance, a pattern that also appears in the ROAD variant. We provide guidelines for more cautious removal-based benchmarking, with implications for validating mechanistic understanding of neural network internals.

An adaptive bandwidth selection procedure for the mixture kernel in the maximum mean discrepancy (MMD) for fitting generative moment matching networks (GMMNs) is introduced, and improved learning of copula random number generators is demonstrated. Based on the relative error of the training loss, the number of kernels is increased during training; additionally, the relative error of the validation loss is used as an early stopping criterion. While training time remains similar, adaptively training GMMNs (AGMMNs) significantly increases training performance, which is shown based on validation MMD trajectories, samples and validation MMD values. Superiority of AGMMNs over GMMNs and parametric copula models is also demonstrated in terms of three applications. First, convergence rates of estimators based on quasi-random versus pseudo-random samples from copulas are investigated in dimensions as large as 100 for the first time. Second, replicated validation MMDs, as well as Monte Carlo and quasi-Monte Carlo applications demonstrate the improved training of AGMMNs for a copula model implied by the 50 constituents of the S&P 500 index after deGARCHing. Last, both the latter dataset and 50 constituents of the FTSE 100 are used to demonstrate that the improved training of AGMMNs indeed translates to an improved model prediction.

The architecture of a neural network and the choice of its activation function are both fundamental to its performance. Equally important is ensuring that these two elements are well matched, as their alignment is key to effective representation and learning. In this paper, we introduce the Fourier Multi-Component and Multi-Layer Neural Network (FMMNN), a model that combines sine-type activations with the multi-component and multi-layer structure of MMNNs. In an FMMNN, each component is represented as a trainable linear combination of fixed random sine-type basis functions, while multi-layer composition generates more complex and adaptive high-frequency features. We establish that FMMNNs retain exponential expressive power for function approximation even under a low-rank architectural structure. We also analyze the optimization landscape of FMMNNs and find it to be substantially more favorable than that of standard fully connected neural networks, especially for high-frequency targets. In addition, we propose a scaled random initialization method for the first-layer weights in FMMNNs, which accelerates training and improves final performance when sufficient samples are available. Extensive numerical experiments support our theoretical insights, showing that FMMNNs achieve strong accuracy and favorable convergence behavior on oscillatory function-approximation benchmarks.

When modeling health events in small areas, the conditional autoregressive (CAR) framework of Besag, York, and Mollié (BYM) is widely used. For multiple outcomes, the multivariate CAR (MCAR) extension accommodates dependence among diseases that share risk factors, in addition to spatial dependence, and can also jointly model demographic subgroups for a single disease, allowing information to be borrowed across related populations. However, recent studies have shown that the BYM CAR model can be overly informative, leading to excessively precise estimates. While the MCAR model is expected to be more informative due to additional information shared across subgroups, its level of informativeness has not been previously quantified. We propose a framework to measure MCAR model informativeness as an extension of prior work and introduce a method to control it, ensuring the model contributes comparably to each subgroup. We achieve this through a reparameterization of the MCAR model within a computationally efficient framework. We demonstrate how the MCAR model compares with the BYM CAR model in terms of informativeness and oversmoothing and highlight the advantages of the restricted MCAR model using county-level heart disease death data stratified by race and sex.

Habitat selection and space use are fundamental to understanding animal distribution. Traditional methods for quantifying habitat preferences from telemetry data assume regular sampling and negligible measurement error. However, these assumptions are routinely violated in marine systems. Practitioners typically regularize and filter the data before fitting models, but these two-step procedures do not propagate uncertainty from the filtering stage and can yield biased estimates. Habitat-driven Langevin diffusion models offer an elegant alternative, naturally accommodating irregular sampling. However, incorporating measurement error via a state-space formulation is challenging because habitat covariates depend on the latent true locations. We address this using the Laplace approximation to simultaneously integrate over true locations and account for habitat covariates along latent paths, yielding a single-stage framework efficiently implemented in Template Model Builder (TMB). By doing so, we provide the first TMB implementation capable of handling covariates that depend on latent variables, allowing inference via fast and efficient maximum likelihood estimation. Simulations show that our approach outperforms the two-step method, recovering habitat-selection parameters even under substantial measurement error and missing data, with more accurate utilization distributions and trajectory reconstructions. Applied to narwhal (Monodon monoceros) telemetry data, the two-step method substantially shrinks the habitat selection coefficient towards zero, while our unified approach recovers a much stronger signal. Our framework offers a computationally efficient solution to long-standing challenges of measurement error and temporal irregularity in habitat selection inference, applicable across a wide range of taxa and environments.

Passive acoustic monitoring holds great promise for ecological inference, yet existing automated tools are typically narrowly trained and non-transferable. We address these limitations with PULSE, a semi-supervised, multi-task framework for Orthoptera bioacoustics, combining weakly-supervised species classification, self-supervised learning on unlabelled field audio, and knowledge distillation from a general-purpose bioacoustic model. Our domain-adapted specialist model outperforms a state-of-the-art general model across all metrics (macro F1: 0.21 vs. 0.07; AUC: 0.74 vs. 0.45; AP: 0.32 vs. 0.19), with active learning further raising F1 to 0.34 and AUC to 0.84. Beyond classification, the learned embeddings encode ecologically meaningful structure, exposed through an interactive visualisation tool for ecological discovery.

Population-adjusted indirect comparisons (PAICs) are widely used to synthesize evidence when randomized controlled trials enroll different patient populations and head-to-head comparisons are unavailable. Although PAICs adjust for observed population differences across trials, adjustment alone does not ensure transportability of estimated effects to decision-relevant populations for health technology assessment (HTA). We examine and formalize transportability in PAICs from an estimand-based perspective. We distinguish conditional and marginal treatment effect estimands and show how transportability depends on effect modification, collapsibility, and alignment between the scale of effect modification and the effect measure. Using illustrative examples, we demonstrate that even when effect modifiers are shared across treatments, marginal effects are generally population-dependent for commonly used non-collapsible measures, including hazard ratios and odds ratios. Conversely, collapsible and conditional effects defined on the linear predictor scale exhibit more favorable transportability properties. We further show that pairwise PAIC approaches typically identify effects defined in the comparator population and that applying these estimates to other populations entails an additional, often implicit, transport step requiring further assumptions. This has direct implications for HTA, where PAIC-derived effects are routinely applied within cost-effectiveness and decision models defined for different target populations. Our results clarify when applying PAIC-derived treatment effects to desired target populations is justified, when doing so requires additional assumptions, and when results should instead be interpreted as population-specific rather than decision-relevant, supporting more transparent and principled use of indirect evidence in HTA and related decision-making contexts.

Time-to-event endpoints are central to evaluating treatment efficacy across disease areas. In clinical trials with time-to-event endpoints, the information available for interim and final analyses is largely determined by the number of observed events rather than by the number of enrolled patients. Interim monitoring therefore requires assessing how many additional events are expected to accrue by scheduled future analysis dates. Quantifying uncertainty around these counts is essential for assessing whether planned information levels are likely to be reached, anticipating delays or event overrunning, and supporting operational decisions while the trial is ongoing. This is especially relevant in pediatric oncology trials, where event accrual is often uncertain. Although methods for predicting time to endpoint maturation are well established, interval prediction for event counts at fixed calendar times remains less developed. We propose a patient-level framework for constructing such intervals at interim analyses of time-to-event trials. Conditionally on the interim data, the future count follows a Poisson--binomial law with patient-specific event probabilities; we estimate this law using a conditional parametric bootstrap. Under standard regularity conditions, the bootstrap is consistent and yields asymptotically calibrated prediction intervals. The framework accommodates staggered entry, patient-level covariates, administrative censoring, random loss to follow-up, and possible dependence between entry dates and loss to follow-up before conditioning on the realised interim data. We study its operating characteristics in simulation studies and illustrate it using a real-world phase III trial in childhood acute lymphoblastic leukaemia.

Joint Species Distribution Models are essential for understanding how ecological covariates shape species communities. However, most existing approaches are limited by rigid parametric distributions for count data and the inability to model how interspecific associations change with those covariates. We introduce joint count transformation models, a novel framework designed to overcome these limitations. Our approach combines distribution-free marginal count transformation models for multiple species with a covariate-dependent latent Gaussian copula to model interspecific correlations, interpretable as Spearman's rank correlation on the observed count scale. All model parameters are estimated efficiently via joint maximum likelihood estimation, implemented in the R package tram. We apply this framework to model the joint abundance of three fish-eating bird species, using seasonality as the primary covariate. Our model successfully captured the complex, species-specific seasonal abundance patterns, including periods of high zero-counts and seasonal shifts in variance. Furthermore, the model revealed strong, seasonally-varying correlations between the species. These findings are consistent with an empirical approach and similar to those from the computationally expensive parametric Bayesian Hierarchical Modelling of Species Communities (HMSC) framework. Consistency, accuracy and feasibility of our approach are demonstrated in a simulation study for up to 10 species.

The Cox proportional hazards model is the most widely used regression model in univariate survival analysis, yet extensions to bivariate survival data remain scarce. We propose two novel extensions based on a Lehmann-type representation of the survival function. The first, the simple Lehmann model, is a direct extension that retains a straightforward structure. The second, the generalized Lehmann model, allows greater flexibility by incorporating three distinct regression parameters and includes the simple Lehmann model as a special case. The models admit a direct interpretation in terms of survival probabilities, providing a transparent, fully semiparametric framework for assessing covariate effects on both marginal survival probabilities and their dependence, without requiring specification of a copula or frailty distribution. To estimate the regression parameters, we build on a pseudo-observation-based approach for bivariate survival data and extend it to the generalized model via a two-step procedure. We establish consistency and asymptotic normality of the resulting estimators. The proposed approach is illustrated through simulation studies and an application to data from the Global Retinoblastoma Outcome Study.

Ordinal outcomes are common in clinical settings where they often represent increasing levels of disease progression or different levels of functional impairment. In this article, we focus on representing the average treatment effect for ordinal outcomes via intrinsic pairwise outcome comparisons captured through win estimands, such as the win ratio and win difference. Recognizing the value of baseline covariate adjustment toward enhanced precision, we first develop propensity score weighting estimators, including both inverse probability weighting (IPW) and overlap weighting (OW), tailored to estimating win estimands. Furthermore, we develop augmented weighting estimators that leverage an additional ordinal outcome regression to potentially improve efficiency over weighting alone. Leveraging the theory of U-statistics, we establish the asymptotic theory for all estimators, and derive closed-form variance estimators to support statistical inference. We also prove that all of the covariate-adjusted estimators do not compromise consistency for the target estimand even when the associated working models are incorrectly specified; hence these covariate-adjusted estimators are model-robust. Through simulations we demonstrate the enhanced efficiency of the weighted estimators over the unadjusted estimator, with the augmented weighting estimators showing a further improvement in efficiency except for extreme cases. Finally, we illustrate our proposed methods with the ORCHID trial, and implement our covariate adjustment methods in an R package winPSW.

Stochastic infectious disease models capture uncertainty in public health outcomes and have become increasingly popular in epidemiological practice. However, calibrating these models to observed data is challenging with existing methods for parameter estimation. Stochastic epidemic models are nonlinear dynamical systems with potentially large latent state spaces, resulting in computationally intractable likelihood densities. We develop an approach to calibrating complex epidemiological models to high-dimensional data using Neural Posterior Estimation, a novel technique for simulation-based inference. In NPE, a neural conditional density estimator trained on simulated data learns to "invert" a stochastic simulator, returning a parametric approximation to the posterior distribution. We introduce a stochastic, discrete-time Susceptible Infected (SI) model with heterogeneous transmission for healthcare-associated infections (HAIs). HAIs are a major burden on healthcare systems. They exhibit high rates of asymptotic carriage, making it difficult to estimate infection rates. Through extensive simulation experiments, we show that NPE produces accurate posterior estimates of infection rates with greater sample efficiency compared to Approximate Bayesian Computation (ABC). We then use NPE to fit our SI model to an outbreak of carbapenem-resistant Klebsiella pneumoniae in a long-term acute care facility, finding evidence of location-based heterogeneity in patient-to-patient transmission risk. We argue that our methodology can be fruitfully applied to a wide range of mechanistic transmission models and problems in the epidemiology of infectious disease.

The ongoing electrification and integration of renewable energy sources in Denmark's distribution grids pose significant operational challenges, including insufficient reserve capacity, component degradation due to overload, voltage instability, and increasing infrastructure investment requirements. This article argues that implicit demand-side flexibility (DSF) incentivized through dynamic tariffs offers the most scalable and cost-effective approach to address these challenges in a modern distribution network. We demonstrate that while explicit flexibility mechanisms provide operational certainty, they cannot scale to address system-wide congestion across heterogeneous customer bases. Drawing on empirical consumption data showing strong price-responsive behavior, varying prices due to, e.g., regulatory frameworks including the Danish Market Model 3.0 and Tariff Model 3.0, and economic analysis, we demonstrate potential grid savings of 13--48 million DKK per constrained substation through deferred or avoided reinforcement. We argue that implicit DSF mechanisms represent the necessary pathway for revenue-neutral scalable flexibility solutions that can defer costly grid reinforcements while maintaining system reliability. Beyond direct grid savings, additional value streams include avoided peak generation costs, reduced connection delays, and lower outage risk, further strengthening the economic case. Critically, dynamic tariffs offer the mechanism through which real-time grid constraints can be communicated to consumers, enabling price signals that accurately reflect the actual state of the capacity of the distribution network at any given point in time and space.

In aerospace certification and other safety-critical domains, conservative quantile estimation such as A- and B-basis values is essential to guarantee reliability. While these metrics are traditionally derived from experimental campaigns, this work focuses on their estimation using a validated deterministic numerical model. The problem is formulated under mixed aleatory-epistemic uncertainty, accounting for limited material data, finite sampling effects, and surrogate modeling errors. We propose a methodology for estimating conservative design quantiles with statistical guarantees under mixed uncertainties. The proposed method leverages importance sampling and control variates to achieve accurate and efficient estimates within a fixed computational budget. One key point is the surrogate model's role solely as a variance reduction device, which guarantees unbiased and consistent quantile estimation. By explicitly integrating all sources of uncertainty, the proposed framework provides a numerical alternative to estimate A-basis and B-Basis. Furthermore, Sobol-based sensitivity indices are obtained at no additional cost, offering insight into the dominant epistemic sources. Numerical experiments on structural models demonstrate the method's reliability and computational efficiency. In particular, the application to large-scale industrial simulations confirms its suitability for aerospace certification workflows and highlights its relevance for real world engineering environments.

To enable a numerical handling of uncertainties in composite structures, this work presents a stochastic finite-element framework aimed at improving the reliability assessment of aerospace composites, with particular attention to stiffener debonding. By representing interface variability between laminate parts with spatially correlated random fields, the method aims at considering scattering effect at a higher scale of simulation and testing. A parametric study carried out on standardized Mode I and Mode II fracture tests reveals that the correlation length is the primary driver of observed variability, while the regularity of the covariance kernel has only a marginal impact. To guarantee industrial relevance, we demonstrate that this key parameter can be extracted from experimental fracture data using an Approximate Bayesian Computation approach. The proposed methodology therefore offers a robust route to high-fidelity virtual testing and to the predictive management of uncertainties in the design of damage-tolerant composite airframes.

Donald Trump won the 2024 US Presidential Election despite polls predicting a Democratic lead, echoing the polling miss in 2016. Using the data defect correlation framework, we revisit the 60,000-respondent Cooperative Election Study and find that non-response bias for Trump voters persists on the same order of magnitude ($ρ=-0.0030$ vs $-0.0045$ in 2016) even under sample-matching to the US adult population. We additionally find evidence of positive response bias for Harris voters after adjusting for turnout. Consistent with findings in 2016, polling errors scale with state population size, and larger samples produce greater departures from conventional confidence intervals, with reductions of effective sample size exceeding 99% in the largest states. We propose a pre-election bias correction estimator informed by historical data defect correlations and turnout rates that decreases RMSE from 0.13 to 0.05 using only prior election data, comparable to post-election weighting (RMSE 0.09).

Racial disproportionality in stop and search practices elicits substantial concerns about its societal and behavioral impacts. In London, Black individuals are about four times more likely to be stopped and searched than White individuals. Using data on stop and search events in London from January 2019 to December 2023, this paper aims to investigate disproportionality in the volume of stops for expressive crimes involving Black individuals compared to other ethnicities. We employ a semi-parametric partially linear structural regression method and introduce a Bayesian empirical likelihood procedure combined with double machine learning techniques to control for high-dimensional confounding and to accommodate strong prior assumptions. In addition, we show that the proposed procedure yields a valid posterior in terms of coverage. Applying this approach to the stop and search dataset, we find that racial disproportionality aimed at the Black community may be influenced by the borough racial composition when focusing on expressive crimes.

Using thematic maps to publish statistical information has become a popular visualization. As is the case with all statistical publications, thematic maps also have to deal with the balance between disclosure risk and utility. However, most risk and utility measures do not take into account the spatial character of a map. Some of the proposed spatial risk measures suffer from the Modifiable Areal Unit Problem (MAUP): slightly changing regional classifications may influence the risk. Indeed, even a small translation of for example a grid may influence that risk. We propose a new risk measure that does not suffer from MAUP. Moreover, our risk is directly related to the local density of the (target) population and takes into account that often multiple units may be connected to a single location. We show the behavior of our risk measure using an example dataset of fake but realistic locations of enterprises. Our risk measure can be adapted to take into account the effect on the (perceived) risk of zooming in or out and the effect of the used resolution.

Non-probability data sources are increasingly considered in small area estimation, but inverse probability weighting (IPW) gives model-dependent domain estimators whose reliability may vary substantially across domains. Standard Fay-Herriot (FH) smoothing borrows strength across domains, yet it uses the supplied area-level variance estimates as if they fully described the uncertainty of the input estimators. This can be misleading when some domains have weak coverage, unstable weights, or poor auxiliary balance, since these features may indicate selection-bias risk not captured by the estimated variance alone. We propose a diagnostics-guided variance-inflated FH estimator for finite-population domain totals. The method starts from calibrated IPW domain estimators, summarizes their reliability through a small set of domain diagnostics, and introduces a mixture variance-inflation component in the FH observation equation. Domains whose diagnostics indicate weaker IPW information are thereby smoothed more strongly toward the area-level regression mean. A truth-known validation based on a pseudo-real population of Lithuanian business enterprises shows a substantial reduction in estimation error relative to calibrated IPW.

There is a proliferation of work arguing for the use of synthetic data in scientific research. For example, social scientists are arguing for the use of LLM-generated "silicon samples" in pilot studies; AI evaluations increasingly rely on "LLM-as-a-judge" outputs; and proteomics research is accelerated by generative models that produce synthetic protein structures. These developments raise an intriguing possibility: synthetic data may help researchers ask more questions, run more studies, and accelerate discovery. But they also raise a fundamental concern: synthetic data can be biased, noisy, and misspecified. In this work, we propose statistical principles for using synthetic data in scientific research with provable validity guarantees. The key insight is a new technical condition that we call task exchangeability. Informally, this is a requirement that the researcher can identify historical tasks, for which real data is available, such that their current task of interest is exchangeable with the historical tasks in an appropriate mathematical sense. We develop methods for valid inference under task exchangeability, together with extensions that provide guarantees even beyond exchangeability. We demonstrate the framework on public opinion surveys with silicon samples and AI evaluation with autoraters.

We develop a new, differentially private mean estimator called the balloon mean. The main features of the balloon mean are that it is computationally tractable and enjoys robustness to outlying observations. It is based on an iterative clipping procedure over expanding Mahalanobis balls, or ``balloons.'' The method satisfies zero-concentrated differential privacy and depends on a small number of interpretable tuning parameters. We provide theoretical guarantees under heavy-tailed and contaminated elliptical models, characterizing its statistical performance and robustness to outliers. Extensive simulations demonstrate that the balloon mean is robust to heavy-tailed and contaminated data, and outperforms existing differentially private mean estimators in contaminated settings.

Distributionally robust optimisation (DRO) minimises the worst-case expected loss over an ambiguity set that can capture distributional shifts in out-of-sample environments. While Huber (linear-vacuous) contamination is a classical minimal-assumption model for an $\varepsilon$-fraction of arbitrary perturbations, including it in an ambiguity set can make the worst-case risk infinite and the DRO objective vacuous unless one imposes strong boundedness or support assumptions. We address these challenges by introducing bulk-calibrated credal ambiguity sets: we learn a high-mass bulk set from data while considering contamination inside the bulk and bounding the remaining tail contribution separately. This leads to a closed-form, finite $\mathrm{mean}+\sup$ robust objective and tractable linear or second-order cone programs for common losses and bulk geometries. Through this framework, we highlight and exploit the equivalence between the imprecise probability (IP) notion of upper expectation and the worst-case risk, demonstrating how IP credal sets translate into DRO objectives with interpretable tolerance levels. Experiments on heavy-tailed inventory control, geographically shifted house-price regression, and demographically shifted text classification show competitive robustness-accuracy trade-offs and efficient optimisation times, using Bayesian, frequentist, or empirical reference distributions.

Fairness audits are a key component of responsible machine-learning deployment. Yet, audit-recommendation reliability under incomplete protected-label access is still poorly understood. In this work, we focused on protected-label missingness in fairness mitigation audits. We introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement already present under complete labels. Across ACS/Folktables tasks, missingness settings that retain some protected labels usually do not move selected mitigation methods beyond a complete-label seed-to-seed baseline. At $0%$ protected-label access, candidates collapse to an empirical-risk-minimization baseline and deterministic tie-breaking rather than revealing a broad missingness effect. We also found that threshold optimization can turn fairness gains on a single protected axis into intersectional harm above a seed baseline, and this threshold-optimizer finding persists under random-forest validation. Overall, our results highlight that protected-label missingness should be reported with seed-null calibration, candidate-set context, and intersectional consequences before it is treated as evidence of audit fragility.

In multi-class classification problems, classes often have a natural priority ordering (e.g., cancer stages, COVID-19 severity levels, or air-quality categories). In such settings, it is important to prioritize correct identification of more severe classes and to control under-classification errors, which occur when an observation from a higher-priority class is misclassified into a lower-priority one. The Hierarchical Neyman-Pearson (H-NP) framework of Wang et al. (2024) was developed for ordered multi-class settings to prioritize under-classification error control; its H-NP umbrella algorithm provides high-probability control of under-classification errors at user-specified levels. This paper introduces the R package HNPclassifier, which implements H-NP umbrella algorithms to construct H-NP classifiers using built-in learners such as logistic regression, random forests, and support vector machines, as well as user-supplied scoring functions, thereby enabling effective error control for ordered multi-class classification tasks.

The OSIRIS-REx mission acquired spatially resolved (2-10 m spot sizes) visible-near infrared (VNIR) and thermal infrared (TIR) spectra across four candidate sampling sites on asteroid (101955) Bennu: Nightingale, Osprey, Sandpiper, and Kingfisher. To quantify heterogeneity across a small body (about 500 m radius) like Bennu, we explore remotely observed spectral data to draw conclusions about the mineralogical composition and key physical processes that drive surface variability. We derive diagnostic band parameters from the OSIRIS-REx Visible and Infrared Spectrometer and the OSIRIS-REx Thermal Emission Spectrometer datasets to quantify compositional and physical variability across sites and assess their mineralogical context. The VNIR spectra exhibit similar overall reflectance shapes but systematic differences in spectral slopes and the 2.74 micron OH absorption. TIR emissivity spectra reveal modest but statistically significant shifts in the Christiansen Feature, silicate stretching, and bending band positions, indicating differences in silicate composition, hydration state, and Mg/Fe relative abundance. Principal component analysis separates each site into distinct clusters in multivariate band-parameter space, whereas K-means clustering identifies intra-site spectral sub-populations. Welch's Analysis of Variance and Hotelling's tests confirm that band-parameter variations between sites are significant. These results reveal that Bennu's surface preserves measurable spectral heterogeneity at 2-10 m scales, with site-to-site variations in hydration indicators and silicate band positions. The spectral properties of Nightingale encompass the full range observed across all four sites, establishing a remote sensing baseline for contextualizing laboratory analyses of the returned sample within Bennu's broader composition diversity and alteration history.

Organizations increasingly deploy AI as a low-cost prediction layer in customer-facing decision processes, including demand sensing, service-quality monitoring, product testing, and market research, but AI-generated signals are unevenly reliable across tasks, products, and customer segments. Firms therefore still need scarce human validation (labels, audits, survey responses, or follow-up measurements) to anchor AI outputs to ground truth. Because human ground truth is itself noisy, varying across labelers and even across repeated judgments, the firm must collect and average several human labels per task, which makes human validation costly. We study how to allocate a limited human-validation budget across many AI-assisted tasks when reliability is heterogeneous and unknown before deployment. We cast this within tuned prediction-powered inference. Each human label both sharpens the AI-assisted estimate and reveals the task's rectification difficulty, the variance that remains after the AI prediction is optimally used as a control variate. If difficulties were known, the optimal allocation would follow a Neyman square-root rule; because they are unknown, we propose a policy based on upper confidence bounds that learns them online and steers validation toward tasks where AI is least reliable. We prove that the policy's terminal efficiency loss relative to the oracle allocation vanishes as the budget grows. In synthetic experiments and a real digital-twin survey with 68 tasks and over 2000 respondents, it closes most of the gap to the oracle when reliability is heterogeneous, outperforming uniform and epsilon-greedy allocation; on the survey data it also outperforms explore-then-commit pilot designs and cuts uniform's 10--12% gap to 2--6%. The value of AI depends not only on model accuracy but also on the operational policy that targets human oversight where AI errors matter most.

Structure-based and ligand-based computational drug design have traditionally relied on disjoint data sources and modeling assumptions, limiting their joint use at scale. In this work, we introduce Contrastive Geometric Learning for Unified Computational Drug Design (ConGLUDe), a single contrastive geometric model that unifies structure- and ligand-based training. ConGLUDe couples a geometric protein encoder that produces whole-protein representations and implicit embeddings of predicted binding sites with a fast ligand encoder, removing the need for predefined pockets. By aligning ligands with both global protein representations and multiple candidate binding sites through contrastive learning, ConGLUDe supports ligand-conditioned pocket prediction in addition to virtual screening and target fishing, while being trained jointly on protein-ligand complexes and large-scale bioactivity data. Across diverse benchmarks, ConGLUDe achieves competitive zero-shot virtual screening performance, substantially outperforms existing methods on a challenging target fishing task, and demonstrates state-of-the-art ligand-conditioned pocket selection. These results highlight the advantages of unified structure-ligand training and position ConGLUDe as a step toward general-purpose foundation models for drug discovery.

We present a suite of packages in R, Python, Julia, and C++ that efficiently solve the Sorted L-One Penalized Estimation (SLOPE) problem. The packages feature a highly efficient hybrid coordinate descent algorithm that fits generalized linear models (GLMs) and supports a variety of loss functions, including Gaussian, binomial, Poisson, and multinomial logistic regression. Our implementation is designed to be fast, memory-efficient, and flexible. The packages support a variety of data structures (dense, sparse, and out-of-memory matrices) and are designed to efficiently fit the full SLOPE path as well as handle cross-validation of SLOPE models, including the relaxed SLOPE. We present examples of how to use the packages and benchmarks that demonstrate the performance of the packages on both real and simulated data and show that our packages outperform existing implementations of SLOPE in terms of speed.

High-resolution estimates of population health indicators are critical for precision public health. We propose a method for high-resolution estimation that fuses distinct data sources: an unbiased, low-resolution data source (e.g. aggregated administrative data) and a potentially biased, high-resolution data source (e.g. individual-level online survey responses). We assume that the potentially biased, high-resolution data source is generated from the population under a model of sampling bias where observables can have arbitrary impact on the probability of response but the difference in the log probabilities of response between units with the same observables is linear in the difference between sufficient statistics of their observables and outcomes. Our data fusion method learns a distribution that is closest (in the sense of KL divergence) to the online survey distribution and consistent with the aggregated administrative data and our model of sampling bias. This approach significantly reduces bias in high-resolution estimates compared to baselines that rely on a single data source alone on a testbed that includes repeated measurements of three indicators measured by both the (online) Household Pulse Survey and ground-truth data sources at two geographic resolutions over the same time period.

A novel, stochastic approach to amputation, the process of introducing missing values to a complete dataset, is presented. It allows one to construct a wide variety of missingness patterns by only having to specify distributions of missingness indicators as opposed to specifying each missingness pattern manually. Missingness indicators are modeled in a principled way via copulas and Bernoulli margins, thus allowing one to incorporate dependence in missingness patterns. Besides more classical missingness mechanisms such as missing completely at random, missing at random, and missing not at random, the approach is able to model structured missingness such as block missingness and, via mixtures, monotone missingness, which are patterns of missing data frequently found in real-life datasets. Properties such as joint missingness probabilities or missingness correlation are derived mathematically. The flexibility of the approach in capturing different missingness patterns while only requiring to specify distributional assumptions on missingness indicators is demonstrated with mathematical examples and empirical illustrations in terms of a well-known example dataset of sufficiently small sample size that allows to identify each missing data point visually. Finally, an example application to multivariate financial time series is provided.

Ensuring robot safety can be challenging; user-defined constraints can miss edge cases, policies can become unsafe even when trained from safe data, and safety can be subjective. Thus, we learn about robot safety by showing policy trajectories to a human who flags unsafe behavior. From this binary feedback, we use the statistical method of conformal prediction to identify a region of states, potentially in learned latent space, guaranteed to contain a user-specified fraction of future policy errors. Our method is sample-efficient, as it builds on nearest neighbor classification and avoids withholding data as is common with conformal prediction. By alerting if the robot reaches the suspected unsafe region, we obtain a warning system that mimics the human's safety preferences with guaranteed miss rate. From video labeling, our system can detect when a quadcopter visuomotor policy will fail to steer through a designated gate. We present an approach for policy improvement by avoiding the suspected unsafe region. With it we improve a model predictive controller's safety, as shown in experimental testing with 30 quadcopter flights across 6 navigation tasks. Code and videos are provided.

A refined statistical understanding of LLM pre-training requires the analysis of the transformer architecture for data distributions that encapsulate key characteristics of text data. To address this, we propose a text data distribution based on an extension of the log-bilinear language model from the natural language processing literature. For this data generating process, we derive generalization bounds for deep transformer architectures, highlighting the dependence on the network architecture, the vocabulary size, the number of documents and the document length.

Variational methods are widely used to approximate posterior distributions in Bayesian inference when exact computation is infeasible. We study when such approximations inherit posterior consistency. Our first result shows that, on a general metric space, a uniform bound on the Kullback--Leibler divergence from the approximating measures to a tight sequence of target measures forces the approximating sequence to be tight. It follows that if the target posteriors converge weakly to a Dirac mass at the true parameter, then any variational sequence with bounded Kullback--Leibler divergence to the targets is also consistent. We also give simple logarithmic-moment conditions that verify this boundedness condition, and illustrate them for smooth generalised posterior distributions.

This article investigates stochastic processes taking values in metric spaces that lack a topological vector space structure, a regime characterized by intricate interplay between topological, geometric, and temporal dependence structures. It is formally established that spaces admitting an isometric Hilbertian embedding constitute a strict subclass within the much broader class of metric spaces possessing the ball property. While traditional kernel methods are susceptible to geometric distortion when the underlying space cannot be isometrically embedded into a Hilbert space, we bypass such limitations by exploiting a fundamental structural property inherent to this broader class; namely, that Borel probability measures are uniquely determined by their values on balls. These separating classes provide the foundation for the subsequently introduced measure-theoretic inference methodology. We derive uniform convergence of a family of time-dependent random measures, alongside weak invariance principles for the corresponding nonstationary random fields. This framework explicitly exposes how dependence and geometric complexity influence sample path regularity. Furthermore, because the rapid decay of small-ball probabilities can prohibit the existence of limiting distributions for supremum-based discrepancy measures, we develop $L^p$-based alternatives. By directly leveraging the introduced convergence results, this approach circumvents the need for higher-order $U$-process formulations. Finally, for spaces that do admit an isometric Hilbertian embedding, and where $U$-processes naturally arise, we establish limit theory for both degenerate and nondegenerate multi-parameter $U$-processes, and demonstrate that local discrepancy tests maintain asymptotic stability under dynamic parameter regimes.

Consider Schott's statistic (Schott, 2005) defined as the squared Frobenius norm of the sample correlation matrix for data from $α$-regularly varying populations. We investigate its asymptotic distribution in a general framework characterized by data dimension p, sample size n, and regularly varying coefficients $α$. In particular, we identify a phase transition phenomenon in the asymptotic behavior. For light-tailed populations ($α> 3$), we revisit the $α$-free asymptotic distribution but relax the constraint on the ratio of $p/n$. For heavy-tailed populations ($α< 3$), we derive a new asymptotic normal distribution whose variance explicitly depends on $α$. We also propose a consistent estimator for the asymptotic variance such that the standardized Schott's test statistic remains applicable for unknown location parameters and all $α> 0$.

Assessing structural performance under seismic hazard requires accounting for both damage accumulation and post-event recovery. In current performance-based earthquake engineering (PBEE), recovery is generally treated as a post-processing attribute, while structural performance is modeled using Poissonian exceedance assumptions that imply renewability and memorylessness. These assumptions hinder a unified treatment of reliability and resilience under repeated seismic loading. This study proposes a generalized PBEE framework in which damage and recovery are embedded directly into the system dynamics through a continuous-time Markov chain. A single generator matrix governs state-dependent transitions, providing a unified description of structural reliability and resilience while remaining compatible with standard PBEE metrics. Time-dependent failure probabilities and reliability indices are derived from the transient system dynamics, whereas resilience is quantified through the expected fraction of operational time before collapse. The framework exploits the spectral properties of the generator matrix to compute both metrics efficiently and transparently. The methodology is illustrated on a three-state example and applied to two structural archetypes: a braced frame and a base-isolated system. Results show that recovery dynamics can strongly affect long-term resilience even when conventional reliability measures exhibit limited sensitivity, emphasizing the need to explicitly account for recovery in life-cycle seismic performance assessment.

We study Toeplitz covariance estimation when fixed-threshold one-bit quantization is combined with deterministic sparse-ruler sampling, so that each observed bit is reused across many lag products. At a nonzero threshold the signs have nonzero mean, and this reuse gives raw sign products a coherent one-vertex variance component governed by weighted row sums; centering removes it and leaves a degenerate sparse-pair statistic. We prove a Gaussian variance contraction theorem for hollow quadratic forms of bounded coordinate transforms, including hard threshold signs: the variance is bounded by the squared correlation operator norm times the squared Frobenius norm of the edge weights, with constants independent of dimension, support size and maximum degree. For the oracle centered sparse-ruler estimator, the leading operator-norm term is \(γ_0L_1κ_{\rm obs}\sqrt{φ(Ω)\log d/n}\), where \(φ(Ω)=\sum_{s=1}^{d-1}q_s^{-1}\) is the coverage coefficient of the ruler; pooled marginal calibration from the \(n|Ω|\) observed bits adds a plug-in term. A spectral-packing lower bound in a known-scale identity-neighborhood submodel shows that this dependence is intrinsic under balanced coverage geometry; in the non-saturated regime where the coverage term dominates, the oracle estimator is minimax rate optimal over this submodel.

Since the introduction of network psychometrics, several connections to statistical models in "classical" psychometrics (i.e., IRT, SEM, GLM) as well as to approaches from other research fields have been established. In this paper, these developments have been reviewed and synthesized and, based on an exploratory literature search, further advanced and presented in an accessible visual format. This perspective opens up promising opportunities to extend the psychometric-toolbox by incorporating and learning from statistical methodologies developed in other research domains, which often address similar or even identical problems. Highlighting these methodological commonalities may also foster collaboration across research fields that have traditionally remained largely independent. Moreover, awareness of these connections may render methodological development more systematic and goal-directed and may enable a meaningful division of labor, for example between the development of statistical methodology and its practical implementation for empirical research through software tools. Finally, these methodological advances provide new opportunities for empirical research and may contribute to a reconciliation with longstanding conceptual issues concerning psychometric constructs and, more broadly, psychological phenomena.

We address the classical problem of constructing confidence intervals (CIs) for the mean of a distribution, given \(N\) i.i.d. samples, such that the CI contains the true mean with probability at least \(1 - δ\), where \(δ\in (0,1)\). We characterize three distinct learning regimes based on the minimum achievable limiting width of any CI as the sample size \(N_δ \to \infty\) and \(δ\to 0\). In the first regime, where \(N_δ\) grows slower than \(\log(1/δ)\), the limiting width of any CI equals the width of the distribution's support, precluding meaningful inference. In the second regime, where \(N_δ\) scales as \(\log(1/δ)\), we precisely characterize the minimum limiting width, which depends on the scaling constant. In the third regime, where \(N_δ\) grows faster than \(\log(1/δ)\), complete learning is achievable, and the limiting width of the CI collapses to zero, converging to the true mean. We demonstrate that CIs derived from concentration inequalities based on Kullback--Leibler (KL) divergences achieve asymptotically optimal performance, attaining the minimum limiting width in both sufficient and complete learning regimes for distributions in two families: single-parameter exponential and bounded support. Additionally, these results extend to one-sided CIs, with the width notion adjusted appropriately. Finally, we generalize our findings to settings with random per-sample costs, motivated by practical applications such as stochastic simulators and cloud service selection. Instead of a fixed sample size, we consider a cost budget \(C_δ\), identifying analogous learning regimes and characterizing the optimal CI construction policy.

Fisher's fiducial probability has recently attracted renewed attention under the notion of epistemic confidence. Epistemic confidence statements can be formulated through extended likelihoods, thereby clarifying several long-standing controversies regarding its fiducial probability properties. It establishes a direct connection between Fisher's epistemic notion of confidence for observed data and Neyman's frequentist aleatory coverage probability for future data, thereby enabling extension of epistemic confidence statements for multidimensional parameters. We demonstrate how higher-order asymptotic theory can be applied to refine the first-order asymptotic epistemic confidence statements of the observed region, as a direct consequence of extended likelihood property.

We study nonparametric Bayesian binary classification, in the case where the unknown probability response function is possibly spatially inhomogeneous, for example, being generally flat across the domain but presenting localized sharp variations. We consider a hierarchical procedure based on the Besov-Laplace priors from the inverse problems and imaging literature, with a carefully tuned hyper-prior on the regularity parameter. We show that the resulting posterior distribution concentrates towards the ground truth at optimal rate, automatically adapting to the unknown regularity. To implement posterior inference in practice, we devise an efficient Markov chain Monte Carlo (MCMC) algorithm based on recent ad-hoc dimension-robust methods for Besov-Laplace priors. We then test the considered approach in extensive numerical simulations, where we obtain a solid corroboration of the theoretical results.

Defining a distance in a mixed setting requires the quantification of observed differences of variables of different types and of variables that are measured on different scales. There exist several proposals for mixed variable distances, however, such distances tend to be biased towards specific variable types and measurement units. That is, the variable types and scales influence the contribution of individual variables to the overall distance. In this paper, we define unbiased mixed variable distances for which the contributions of individual variables to the overall distance are not influenced by measurement types or scales. We define the relevant concepts to quantify such biases and we provide a general formulation that can be used to construct unbiased mixed variable distances.

Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during training to provide suitable "target" dynamics useful for performing the task. Because it exploits the full recurrent connectivity, the method produces networks that perform tasks with fewer neurons and greater noise robustness than traditional least-squares (FORCE) approaches. In addition, we show how introducing additional input signals into the target-generating network, which act as task hints, greatly extends the range of tasks that can be learned and provides control over the complexity and nature of the dynamics of the trained, task-performing network.