We introduce autoregressive implicit quantile networks (AIQN), a fundamentally different approach to generative modeling than those commonly used, that implicitly captures the distribution using quantile regression. AIQN is able to achieve superior perceptual quality and improvements in evaluation metrics, without incurring a loss of sample diversity. The method can be applied to many existing models and architectures. In this work we extend the PixelCNN model with AIQN and demonstrate results on CIFAR-10 and ImageNet using Inception score, FID, non-cherry-picked samples, and inpainting results. We consistently observe that AIQN yields a highly stable algorithm that improves perceptual quality while maintaining a highly diverse distribution.
This paper considers the quantile regression approach for partially linear spatial autoregressive models with possibly varying coefficients. B-spline is employed for the approximation of varying coefficients. The instrumental variable quantile regression approach is employed for parameter estimation. The rank score tests are developed for hypotheses on the coefficients, including the hypotheses on the non-varying coefficients and the constancy of the varying coefficients. The asymptotic properties of the proposed estimators and test statistics are both established. Monte Carlo simulations are …
Spatial dependent data frequently occur in many fields such as spatial econometrics and epidemiology. To deal with the dependence of variables and estimate quantile-specific effects by covariates, spatial quantile autoregressive models (SQAR models) are introduced. Conventional quantile regression only focuses on the fitting models but ignores the examination of multiple conditional quantile functions, which provides a comprehensive view of the relationship between the response and covariates. Thus, it is necessary to study the different regression slopes at different quantiles, especially in …
An important issue is that the respiratory mortality may be a result of air pollution which can be measured by the following variables: temperature, relative humidity, carbon monoxide, sulfur dioxide, nitrogen dioxide, hydrocarbons, ozone and particulates. The usual way is to fit a model using the ordinary least squares regression, which has some assumptions, also known as Gauss-Markov assumptions, on the error term showing white noise process of the regression model. However, in many applications, especially for this example, these assumptions are not satisfied. Therefore, in this study, a qu…
We introduce a simple modification to the standard maximum likelihood estimation (MLE) framework. Rather than maximizing a single unconditional likelihood of the data under the model, we maximize a family of \textit{noise conditional} likelihoods consisting of the data perturbed by a continuum of noise levels. We find that models trained this way are more robust to noise, obtain higher test likelihoods, and generate higher quality images. They can also be sampled from via a novel score-based sampling scheme which combats the classical \textit{covariate shift} problem that occurs during sample …
Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural network (RNN) models the conditional distribution over the next element conditioned on all previous elements. In this paradigm, the bottleneck is the extent to which the RNN can model long-range dependencies, and the most successful approaches rely on causal convolutions, which offer better access to earlier parts of the sequence than conventional RNNs. Taki…
Deep sub-ensembles meets quantile regression: uncertainty-aware imputation for time series
Department of Computer and Information（计算机与信息系）；Hefei University of Technology（合肥工业大学）；Dept. of Comp. Sci. & Tech.（计算机科学与技术系）；Tsinghua University（清华大学）
Jilin University（吉林大学）；Zhuhai College of Jilin University（吉林大学珠海学院）
Flow-based generative models are a family of exact log-likelihood models with tractable sampling and latent-variable inference, hence conceptually attractive for modeling complex distributions. However, flow-based models are limited by density estimation performance issues as compared to state-of-the-art autoregressive models. Autoregressive models, which also belong to the family of likelihood-based methods, however suffer from limited parallelizability. In this paper, we propose Dynamic Linear Flow (DLF), a new family of invertible transformations with partially autoregressive structure. Our…
E-QRGMM: Efficient Generative Metamodeling for Covariate-Dependent Uncertainty Quantification
School of Data Science（数据科学学院）；School of Management（管理学院）；Department of Decision Analytics and Operations, College of Business, City University of Hong Kong（商业学院决策分析与运营系，香港城市大学）；The Laboratory for AI-Powered Financial Technologies（人工智能赋能金融技术实验室）
Learning to Simulate: Generative Metamodeling via Quantile Regression
Department of Industrial and Systems Engineering, University of Minnesota（明尼苏达大学工业与系统工程系）；School of Data Science, Fudan University（复旦大学数据科学学院）；School of Management, Fudan University（复旦大学管理学院）；Department of Decision Analytics and Operations, City University of Hong Kong（香港城市大学决策分析与运营系）；Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology（香港科技大学工业工程与决策分析系）
Deep autoregressive models compute point likelihood estimates of individual data points. However, many applications (i.e., database cardinality estimation) require estimating range densities, a capability that is under-explored by current neural density estimation literature. In these applications, fast and accurate range density estimates over high-dimensional data directly impact user-perceived performance. In this paper, we explore a technique, variable skipping, for accelerating range density estimation over deep autoregressive models. This technique exploits the sparse structure of range …
Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance compared to state-of-the-art autoregressive models. In this paper, we investigate and improve upon three limiting design choices employed by flow-based models in prior work: the use of uniform noise for dequantization, the use of inexpressive affine flows, and the use of purely convolutional conditioning networks in coupling layers. Based on our findings, we propose Flow++, a new…
In this paper, a new estimation method is introduced for the quantile spectrum, which uses a parametric form of the autoregressive (AR) spectrum coupled with nonparametric smoothing. The method begins with quantile periodograms which are constructed by trigonometric quantile regression at different quantile levels, to represent the serial dependence of time series at various quantiles. At each quantile level, we approximate the quantile spectrum by a function in the form of an ordinary AR spectrum. In this model, we first compute what we call the quantile autocovariance function (QACF) by the …
Estimating conditional quantiles of financial time series is essential for risk management and many other applications in finance. It is well-known that financial time series display conditional heteroscedasticity. Among the large number of conditional heteroscedastic models, the generalized autoregressive conditional heteroscedastic (GARCH) process is the most popular and influential one. So far, feasible quantile regression methods for this task have been confined to a variant of the GARCH model, the linear GARCH model, owing to its tractable conditional quantile structure. This paper consid…
Melbourne Business School, the University of Melbourne（墨尔本商学院，墨尔本大学）；School of Political Science and Economics, Waseda University（早稻田大学政治经济学院）；Booth School of Business, the University of Chicago（芝加哥大学布斯商学院）
Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Despite their computational efficiency, the density estimation performance of flow-based generative models significantly falls behind those of state-of-the-art autoregressive models. In this work, we introduce masked convolutional generative flow (MaCow), a simple yet effective arch…
Cornell Tech and Cornell University（康奈尔科技校区和康奈尔大学）
Numerous applications of machine learning involve representing probability distributions over high-dimensional data. We propose autoregressive quantile flows, a flexible class of normalizing flow models trained using a novel objective based on proper scoring rules. Our objective does not require calculating computationally expensive determinants of Jacobians during training and supports new types of neural architectures, such as neural autoregressive flows from which it is easy to sample. We leverage these models in quantile flow regression, an approach that parameterizes predictive conditiona…
We introduce a new category of multivariate conditional generative models and demonstrate its performance and versatility in probabilistic time series forecasting and simulation. Specifically, the output of quantile regression networks is expanded from a set of fixed quantiles to the whole Quantile Function by a univariate mapping from a latent uniform distribution to the target distribution. Then the multivariate case is solved by learning such quantile functions for each dimension's marginal distribution, followed by estimating a conditional Copula to associate these latent uniform random va…
Linear quantile regression is a powerful tool to investigate how predictors may affect a response heterogeneously across different quantile levels. Unfortunately, existing approaches find it extremely difficult to adjust for any dependency between observation units, largely because such methods are not based upon a fully generative model of the data. For analyzing spatially indexed data, we address this difficulty by generalizing the joint quantile regression model of Yang and Tokdar (2017) and characterizing spatial dependence via a Gaussian or $t$ copula process on the underlying quantile le…
Great strides have been made in the field of reconstructing past temperatures based on models relating temperature to temperature-sensitive paleoclimate proxies. One of the goals of such reconstructions is to assess if current climate is anomalous in a millennial context. These regression based approaches model the conditional mean of the temperature distribution as a function of paleoclimate proxies (or vice versa). Some of the recent focus in the area has considered methods which help reduce the uncertainty inherent in such statistical paleoclimate reconstructions, with the ultimate goal of …
North Carolina State University（北卡罗来纳州立大学）；London School of Economics and Political Science（伦敦政治经济学院）；ByteDance（字节跳动）；University of Miami（迈阿密大学）
Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy. It is critical in a number of sequential decision making problems ranging from healthcare to technology industries. Most of the work in existing literature is focused on evaluating the mean outcome of a given policy, and ignores the variability of the outcome. However, in a variety of applications, criteria other than the mean may be more sensible. For example, when the reward distribution is skewed and asymmetric, quantile-based metrics are ofte…
While normalizing flows have led to significant advances in modeling high-dimensional continuous distributions, their applicability to discrete distributions remains unknown. In this paper, we show that flows can in fact be extended to discrete events---and under a simple change-of-variables formula not requiring log-determinant-Jacobian computations. Discrete flows have numerous applications. We consider two flow architectures: discrete autoregressive flows that enable bidirectionality, allowing, for example, tokens in text to depend on both left-to-right and right-to-left contexts in an exac…
Here, we propose a general method for probabilistic time series forecasting. We combine an autoregressive recurrent neural network to model temporal dynamics with Implicit Quantile Networks to learn a large class of distributions over a time-series target. When compared to other probabilistic neural forecasting models on real- and simulated data, our approach is favorable in terms of point-wise prediction accuracy as well as on estimating the underlying temporal distribution.
Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of which make trade-offs including run-time, diversity, and architectural restrictions. In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches. These techniques are compared and contrasted, explaining the premises behind each and how they are interrelated,…
Learning graph generative models is a challenging task for deep learning and has wide applicability to a range of domains like chemistry, biology and social science. However current deep neural methods suffer from limited scalability: for a graph with $n$ nodes and $m$ edges, existing deep neural methods require $Ω(n^2)$ complexity by building up the adjacency matrix. On the other hand, many real world graphs are actually sparse in the sense that $m\ll n^2$. Based on this, we develop a novel autoregressive model, named BiGG, that utilizes this sparsity to avoid generating the full adjacency ma…
Universidade Federal de Santa Maria（圣玛丽亚联邦大学）；UFPE（伯南布哥联邦大学）
In this paper, we propose five prediction intervals for the beta autoregressive moving average model. This model is suitable for modeling and forecasting variables that assume values in the interval $(0,1)$. Two of the proposed prediction intervals are based on approximations considering the normal distribution and the quantile function of the beta distribution. We also consider bootstrap-based prediction intervals, namely: (i) bootstrap prediction errors (BPE) interval; (ii) bias-corrected and acceleration (BCa) prediction interval; and (iii) percentile prediction interval based on the quanti…
Neural autoregressive models are explicit density estimators that achieve state-of-the-art likelihoods for generative modeling. The D-dimensional data distribution is factorized into an autoregressive product of one-dimensional conditional distributions according to the chain rule. Data completion is a more involved task than data generation: the model must infer missing variables for any partially observed input vector. Previous work introduced an order-agnostic training procedure for data completion with autoregressive models. Missing variables in any partially observed input vector can be i…
We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data. Successive deep stochastic hidden layers are equipped with autoregressive connections, which enable the model to be sampled from quickly and exactly via ancestral sampling. We derive an efficient approximate parameter estimation method based on the minimum description length (MDL) principle, which can be seen as maximising a variational lower bound on the log-likelihood, with a feedforward neural network implementing approximate inference. We demonstrate state-of-the-art genera…
Normalizing flows, a popular class of deep generative models, often fail to represent extreme phenomena observed in real-world processes. In particular, existing normalizing flow architectures struggle to model multivariate extremes, characterized by heavy-tailed marginal distributions and asymmetric tail dependence among variables. In light of this shortcoming, we propose COMET (COpula Multivariate ExTreme) Flows, which decompose the process of modeling a joint distribution into two parts: (i) modeling its marginal distributions, and (ii) modeling its copula distribution. COMET Flows capture …
Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, which leads to increased efficiency through parallel processing on hardware such as GPUs. However, directly modeling the joint distribution of all tokens simultaneously is challenging, and even with increasingly complex model structures accuracy lags significantly behind autoregressive models. In this paper, we propose a simple, efficient, and effective model for non-autoregressive…
Mila-Quebec AI Institute（米拉-魁北克人工智能研究所）；U. Montreal（蒙特利尔大学）；Nanyang Technological University（南洋理工大学）；Microsoft Research Asia（微软亚洲研究院）；University of Illinois, Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）
Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style conditional modeling (e.g., exposure bias or lack of long-range coherence), severely limiting their ability to model distributions properly. In this paper, we propose a unique method termed E-ARM for training autoregressive generative models that takes advantage of a well-designed energy-based learning objective. By leveraging the extra degree of freedom of the softmax operation…
Autoregressive generative models can estimate complex continuous data distributions, like trajectory rollouts in an RL environment, image intensities, and audio. Most state-of-the-art models discretize continuous data into several bins and use categorical distributions over the bins to approximate the continuous data distribution. The advantage is that the categorical distribution can easily express multiple modes and are straightforward to optimize. However, such approximation cannot express sharp changes in density without using significantly more bins, making it parameter inefficient. We pr…
Seoul National University（首尔国立大学）；Delft University of Technology（代尔夫特理工大学）
This paper proposes a framework which is able to generate a sequence of three-dimensional human dance poses for a given music. The proposed framework consists of three components: a music feature encoder, a pose generator, and a music genre classifier. We focus on integrating these components for generating a realistic 3D human dancing move from music, which can be applied to artificial agents and humanoid robots. The trained dance pose generator, which is a generative autoregressive model, is able to synthesize a dance sequence longer than 5,000 pose frames. Experimental results of generated …
Institute of Neurology, UCL（伦敦大学学院神经病学研究所）；School of Biomedical Engineering and Imaging Sciences, Kings College London（伦敦国王学院生物医学工程与成像科学学院）
Deep generative models are rapidly gaining traction in medical imaging. Nonetheless, most generative architectures struggle to capture the underlying probability distributions of volumetric data, exhibit convergence problems, and offer no robust indices of model uncertainty. By comparison, the autoregressive generative model PixelCNN can be extended to volumetric data with relative ease, it readily attempts to learn the true underlying probability distribution and it still admits a Bayesian reformulation that provides a principled framework for reasoning about model uncertainty. Our contributi…
Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn discrete representations of images which abstract away local detail. We show that autoregressive models conditioned on these representations can produce high-fidelity reconstructions of images, and that we can train autoregressive priors on these representations that produce samples with large-scale coherence. We can recursively apply the learning procedure…
Polygon meshes are an efficient representation of 3D geometry, and are of central importance in computer graphics, robotics and games development. Existing learning-based approaches have avoided the challenges of working with 3D meshes, instead using alternative object representations that are more compatible with neural architectures and training approaches. We present an approach which models the mesh directly, predicting mesh vertices and faces sequentially using a Transformer-based architecture. Our model can condition on a range of inputs, including object classes, voxels, and images, and…
Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging. In this paper we propose to use autoregressive predictive coding (APC), a recently proposed self-supervised objective, as a generative pre-training approach for learning meaningful, non-specific, and transferable speech representations. We pre-train APC on large-scale unlabeled data and conduct transfer learning experiments on three speech applications that require different information about speech characteristics to perform well: speech recognition, speech…
In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opi…
