We study sampling from a target distribution ${ν_* = e^{-f}}$ using the unadjusted Langevin Monte Carlo (LMC) algorithm. For any potential function $f$ whose tails behave like ${\|x\|^α}$ for ${α\in [1,2]}$, and has $β$-Hölder continuous gradient, we prove that ${\widetilde{\mathcal{O}} \Big(d^{\frac{1}β+\frac{1+β}β(\frac{2}α - \boldsymbol{1}_{\{α\neq 1\}})} ε^{-\frac{1}β}\Big)}$ steps are sufficient to reach the $ε$-neighborhood of a $d$-dimensional target distribution $ν_*$ in KL-divergence. This convergence rate, in terms of $ε$ dependency, is not directly influenced by the tail growth rate $α$ of the potential function as long as its growth is at least linear, and it only relies on the order of smoothness $β$. One notable consequence of this result is that for potentials with Lipschitz gradient, i.e. $β=1$, our rate recovers the best known rate ${\widetilde{\mathcal{O}}(dε^{-1})}$ which was established for strongly convex potentials in terms of $ε$ dependency, but we show that the same rate is achievable for a wider class of potentials that are degenerately convex at infinity. The growth rate $α$ starts to have an effect on the established rate in high dimensions where $d$ is large; furthermore, it recovers the best-known dimension dependency when the tail growth of the potential is quadratic, i.e. ${α= 2}$, in the current setup. Our framework allows for finite perturbations, and any order of smoothness ${β\in(0,1]}$; consequently, our results are applicable to a wide class of non-convex potentials that are weakly smooth and exhibit at least linear tail growth.
University of California, Berkeley（加利福尼亚大学伯克利分校）；University of Wisconsin, Madison（威斯康星大学麦迪逊分校）
Langevin Monte Carlo (LMC) is an iterative algorithm used to generate samples from a distribution that is known only up to a normalizing constant. The nonasymptotic dependence of its mixing time on the dimension and target accuracy is understood mainly in the setting of smooth (gradient-Lipschitz) log-densities, a serious limitation for applications in machine learning. In this paper, we remove this limitation, providing polynomial-time convergence guarantees for a variant of LMC in the setting of nonsmooth log-concave distributions. At a high level, our results follow by leveraging the implic…
University of Toronto（多伦多大学）；Vector Institute（矢量研究所）；Borealis AI（Borealis人工智能公司）；LG Toronto AI Lab（LG多伦多人工智能实验室）
We propose a novel approach to analyze generalization error for discretizations of Langevin diffusion, such as the stochastic gradient Langevin dynamics (SGLD). For an $ε$ tolerance of expected generalization error, it is known that a first order discretization can reach this target if we run $Ω(ε^{-1} \log (ε^{-1}) )$ iterations with $Ω(ε^{-1})$ samples. In this article, we show that with additional smoothness assumptions, even first order methods can achieve arbitrarily runtime complexity. More precisely, for each $N>0$, we provide a sufficient smoothness condition on the loss function such …
We study the underdamped Langevin diffusion when the log of the target distribution is smooth and strongly concave. We present a MCMC algorithm based on its discretization and show that it achieves $\varepsilon$ error (in 2-Wasserstein distance) in $\mathcal{O}(\sqrt{d}/\varepsilon)$ steps. This is a significant improvement over the best known rate for overdamped Langevin MCMC, which is $\mathcal{O}(d/\varepsilon^2)$ steps under the same smoothness/concavity assumptions. The underdamped Langevin MCMC scheme can be viewed as a version of Hamiltonian Monte Carlo (HMC) which has been observed to …
Stein Variational Gradient Descent (SVGD) is an important alternative to the Langevin-type algorithms for sampling from probability distributions of the form $π(x) \propto \exp(-V(x))$. In the existing theory of Langevin-type algorithms and SVGD, the potential function $V$ is often assumed to be $L$-smooth. However, this restrictive condition excludes a large class of potential functions such as polynomials of degree greater than $2$. Our paper studies the convergence of the SVGD algorithm for distributions with $(L_0,L_1)$-smooth potentials. This relaxed smoothness assumption was introduced b…
The stochastic gradient Langevin Dynamics is one of the most fundamental algorithms to solve sampling problems and non-convex optimization appearing in several machine learning applications. Especially, its variance reduced versions have nowadays gained particular attention. In this paper, we study two variants of this kind, namely, the Stochastic Variance Reduced Gradient Langevin Dynamics and the Stochastic Recursive Gradient Langevin Dynamics. We prove their convergence to the objective distribution in terms of KL-divergence under the sole assumptions of smoothness and Log-Sobolev inequalit…
Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a novel analysis of ULMC, motivated by two central questions: (1) Can we obtain improved sampling guarantees beyond strong log-concavity? (2) Can we achieve acceleration for sampling? For (1), prior results for ULMC only hold under a log-Sobolev inequality together with a restrictive Hessian smoothness condition. Here, we relax these assumptions by removing the Hessian smoothness condition and by considering distribut…
Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounters scalability issues in high-dimensional problems when demanding high accuracy. To address this, we propose an approximate Thompson sampling strategy, utilizing underdamped Langevin Monte Carlo, where the latter is the go-to workhorse for simulations of high-dimensional posteriors. Based on the standard smoothness and log-concavity conditions, we study the accelerated posterior concentration and sampling using a spec…
LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI实验室）；Department of Statistics, University of Oxford（牛津大学统计系）；Department of Mathematics, Florida State University（佛罗里达州立大学数学系）；Department of Management Science and Information Systems, Rutgers Business School（罗格斯大学商学院管理科学与信息系统系）
Stochastic gradient descent with momentum (SGDm) is one of the most popular optimization algorithms in deep learning. While there is a rich theory of SGDm for convex problems, the theory is considerably less developed in the context of deep learning where the problem is non-convex and the gradient noise might exhibit a heavy-tailed behavior, as empirically observed in recent studies. In this study, we consider a \emph{continuous-time} variant of SGDm, known as the underdamped Langevin dynamics (ULD), and investigate its asymptotic properties under heavy-tailed perturbations. Supported by recen…
In this paper, we consider the underdamped Langevin diffusion (ULD) and propose a numerical approximation using its associated ordinary differential equation (ODE). When used as a Markov Chain Monte Carlo (MCMC) algorithm, we show that the ODE approximation achieves a $2$-Wasserstein error of $\varepsilon$ in $\mathcal{O}\big(d^{\frac{1}{3}}/\varepsilon^{\frac{2}{3}}\big)$ steps under the standard smoothness and strong convexity assumptions on the target distribution. This matches the complexity of the randomized midpoint method proposed by Shen and Lee [NeurIPS 2019] which was shown to be ord…
We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. Our analysis uses relative convexity/smoothness and self-concordance, ideas which originated in convex optimization, together with a new result in optimal transport that generalizes the displacement convexity of the entropy. Unlike prior works, our result both (1) requires much weaker assumptions on the mirror map and the target distribution, and (2) has vanishing bias as the step size tends to zero. In particular, for the task of sampling from a log-concave distribution supported on a c…
We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-order dynamics allow for more flexible discretization schemes, and we develop a specific method that combines splitting with more accurate integration. For a broad class of $d$-dimensional distributions arising from generalized linear models, we prove that the resulting third-order algorithm produces samples from a distribution that is at most $\varepsilon > 0$ in Wasserstein distance from the target distribution in $O\l…
ENSAE, CREST, IP Paris（国立统计与经济行政学校，经济研究与应用统计中心，巴黎综合理工学院）；University of Warwick（华威大学）
In this paper, we provide non-asymptotic upper bounds on the error of sampling from a target density using three schemes of discretized Langevin diffusions. The first scheme is the Langevin Monte Carlo (LMC) algorithm, the Euler discretization of the Langevin diffusion. The second and the third schemes are, respectively, the kinetic Langevin Monte Carlo (KLMC) for differentiable potentials and the kinetic Langevin Monte Carlo for twice-differentiable potentials (KLMC2). The main focus is on the target densities that are smooth and log-concave on $\mathbb R^p$, but not necessarily strongly log-…
Along with the recent advances in scalable Markov Chain Monte Carlo methods, sampling techniques that are based on Langevin diffusions have started receiving increasing attention. These so called Langevin Monte Carlo (LMC) methods are based on diffusions driven by a Brownian motion, which gives rise to Gaussian proposal distributions in the resulting algorithms. Even though these approaches have proven successful in many applications, their performance can be limited by the light-tailed nature of the Gaussian proposals. In this study, we extend classical LMC and develop a novel Fractional LMC …
Discretized Langevin diffusions are efficient Monte Carlo methods for sampling from high dimensional target densities that are log-Lipschitz-smooth and (strongly) log-concave. In particular, the Euclidean Langevin Monte Carlo sampling algorithm has received much attention lately, leading to a detailed understanding of its non-asymptotic convergence properties and of the role that smoothness and log-concavity play in the convergence rate. Distributions that do not possess these regularity properties can be addressed by considering a Riemannian Langevin diffusion with a metric capturing the loca…
We establish generalization error bounds for stochastic gradient Langevin dynamics (SGLD) with constant learning rate under the assumptions of dissipativity and smoothness, a setting that has received increased attention in the sampling/optimization literature. Unlike existing bounds for SGLD in non-convex settings, ours are time-independent and decay to zero as the sample size increases. Using the framework of uniform stability, we establish time-independent bounds by exploiting the Wasserstein contraction property of the Langevin diffusion, which also allows us to circumvent the need to boun…
Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical guarantees have been proven for both asymptotic and finite-time regimes. Algorithmically, LMC-based algorithms resemble the well-known gradient descent (GD) algorithm, where the GD recursion is perturbed by an additive Gaussian noise whose variance has a particular form. Fractional Langevin Monte Carlo (FLMC) is a recently proposed extension of LMC, where the Gaussian noise is replaced by a heavy-tailed α-stable noise. …
Regularization by denoising: Bayesian model and Langevin-within-split Gibbs sampling
Institut Denis Poisson, University of Orléans（德尼·泊松研究所，奥尔良大学）；University of Toulouse, IRIT/INP-ENSEEIHT, CNRS（图卢兹大学，法国国家信息与自动化研究所/国立高等电子、电子技术、计算机与机械学院，法国国家科学研究中心）
本文提出一种基于去噪正则化（RED）的图像反演贝叶斯框架，并设计了内含Langevin Monte Carlo步骤的分裂Gibbs采样算法，通过去模糊等任务验证了其有效性。
University of California, Berkeley（加州大学伯克利分校）；Google Research（谷歌研究院）
Thompson sampling for multi-armed bandit problems is known to enjoy favorable performance in both theory and practice. However, it suffers from a significant limitation computationally, arising from the need for samples from posterior distributions at every iteration. We propose two Markov Chain Monte Carlo (MCMC) methods tailored to Thompson sampling to address this issue. We construct quickly converging Langevin algorithms to generate approximate samples that have accuracy guarantees, and we leverage novel posterior concentration rates to analyze the regret of the resulting approximate Thomp…
Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms
FinTech Thrust, Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）金融科技方向）；School of Mathematical Science, Fudan University（复旦大学数学学院）；Department of Mathematics, Florida State University（佛罗里达州立大学数学系）
Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
College of Computer Science and Technology National University of Defense Technology（计算机科学与技术学院 国防科技大学）；Center for Machine Learning Research (CMLR) Peking University（机器学习研究中心（CMLR） 北京大学）
Columbia University（哥伦比亚大学）；University of Illinois（伊利诺伊大学）；INRIA（法国国家信息与自动化研究所）；Ecole Normale Supérieure（巴黎高等师范学院）；PSL Research University（巴黎文理研究大学）
Mirror descent, introduced by Nemirovski and Yudin in the 1970s, is a primal-dual convex optimization method that can be tailored to the geometry of the optimization problem at hand through the choice of a strongly convex potential function. It arises as a basic primitive in a variety of applications, including large-scale optimization, machine learning, and control. This paper proposes a variational formulation of mirror descent and of its stochastic variant, mirror Langevin dynamics. The main idea, inspired by the classic work of Brezis and Ekeland on variational principles for gradient flow…
On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach
University of Basel（巴塞尔大学）；University of Oslo（奥斯陆大学）；MBZUAI（马克斯·普朗克智能系统研究所）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；Tübingen AI Center（图宾根人工智能中心）
This paper is concerned with the nonparametric item response theory (NIRT) for estimating item characteristic curves (ICCs) and latent abilities of examinees on educational and psychological tests. In contrast to parametric models, NIRT models can estimate various forms of ICCs under mild shape restrictions, such as the constraints of monotone homogeneity and double monotonicity. However, NIRT models frequently suffer from estimation instability because of the great flexibility of nonparametric ICCs, especially when there is only a small amount of item-response data. To improve the estimation …
Alan Turing Institute（艾伦·图灵研究所）；University of Oxford（牛津大学）；Florida State University（佛罗里达州立大学）；Rutgers Business School（罗格斯商学院）；INRIA（法国国家信息与自动化研究所）；École Normale Supérieure（巴黎高等师范学院）；PSL Research University（巴黎文理研究大学）
Gaussian noise injections (GNIs) are a family of simple and widely-used regularisation methods for training neural networks, where one injects additive or multiplicative Gaussian noise to the network activations at every iteration of the optimisation algorithm, which is typically chosen as stochastic gradient descent (SGD). In this paper we focus on the so-called `implicit effect' of GNIs, which is the effect of the injected noise on the dynamics of SGD. We show that this effect induces an asymmetric heavy-tailed noise on SGD gradient updates. In order to model this modified dynamics, we first…
While the Metropolis Adjusted Langevin Algorithm (MALA) is a popular and widely used Markov chain Monte Carlo method, very few papers derive conditions that ensure its convergence. In particular, to the authors' knowledge, assumptions that are both easy to verify and guarantee geometric convergence, are still missing. In this work, we establish $V$-uniformly geometric convergence for MALA under mild assumptions about the target distribution. Unlike previous work, we only consider tail and smoothness conditions for the potential associated with the target distribution. These conditions are quit…
We analyze the oracle complexity of sampling from polynomially decaying heavy-tailed target densities based on running the Unadjusted Langevin Algorithm on certain transformed versions of the target density. The specific class of closed-form transformation maps that we construct are shown to be diffeomorphisms, and are particularly suited for developing efficient diffusion-based samplers. We characterize the precise class of heavy-tailed densities for which polynomial-order oracle complexities (in dimension and inverse target accuracy) could be obtained, and provide illustrative examples. We h…
Athena/Archimedes Research Centre（雅典娜/阿基米德研究中心）；The University of Edinburgh（爱丁堡大学）；Univ. Grenoble Alpes（格勒诺布尔大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Grenoble INP（格勒诺布尔工业大学）；LIG（格勒诺布尔信息与信号处理实验室）
Rutgers Business School（罗杰斯商学院）；Department of Mathematics（数学系）；School of Mathematics and Statistics（数学与统计学学院）；Department of Management Science and Information Systems（管理科学与信息系统系）
We present an improved analysis of the Euler-Maruyama discretization of the Langevin diffusion. Our analysis does not require global contractivity, and yields polynomial dependence on the time horizon. Compared to existing approaches, we make an additional smoothness assumption, and improve the existing rate from $O(η)$ to $O(η^2)$ in terms of the KL divergence. This result matches the correct order for numerical SDEs, without suffering from exponential time dependence. When applied to algorithms for sampling and learning, this result simultaneously improves all those methods based on Dalayan'…
Georgia Institute of Technology（佐治亚理工学院）；Yale University（耶鲁大学）
We study the Unadjusted Langevin Algorithm (ULA) for sampling from a probability distribution $ν= e^{-f}$ on $\mathbb{R}^n$. We prove a convergence guarantee in Kullback-Leibler (KL) divergence assuming $ν$ satisfies a log-Sobolev inequality and the Hessian of $f$ is bounded. Notably, we do not assume convexity or bounds on higher derivatives. We also prove convergence guarantees in Rényi divergence of order $q > 1$ assuming the limit of ULA satisfies either the log-Sobolev or Poincaré inequality. We also prove a bound on the bias of the limiting distribution of ULA assuming third-order smooth…
University of Maryland（马里兰大学）；Microsoft Research India（微软印度研究院）；National University of Singapore（新加坡国立大学）；Princeton University（普林斯顿大学）；DeepMind（深度思维）；JP Morgan AI Research（摩根大通人工智能研究院）
Reinforcement learning is a framework for interactive decision-making with incentives sequentially revealed across time without a system dynamics model. Due to its scaling to continuous spaces, we focus on policy search where one iteratively improves a parameterized policy with stochastic policy gradient (PG) updates. In tabular Markov Decision Problems (MDPs), under persistent exploration and suitable parameterization, global optimality may be obtained. By contrast, in continuous space, the non-convexity poses a pathological challenge as evidenced by existing convergence results being mostly …
We develop new flexible univariate models for light-tailed and heavy-tailed data, which extend a hierarchical representation of the generalized Pareto (GP) limit for threshold exceedances. These models can accommodate departure from asymptotic threshold stability in finite samples while keeping the asymptotic GP distribution as a special (or boundary) case and can capture the tails and the bulk jointly without losing much flexibility. Spatial dependence is modeled through a latent process, while the data are assumed to be conditionally independent. Focusing on a gamma-gamma model construction,…
Boston University（波士顿大学）；Northeastern University（东北大学）；Massachusetts Institute of Technology（麻省理工学院）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Understanding the shape of a distribution of data is of interest to people in a great variety of fields, as it may affect the types of algorithms used for that data. We study one such problem in the framework of distribution property testing, characterizing the number of samples required to to distinguish whether a distribution has a certain property or is far from having that property. In particular, given samples from a distribution, we seek to characterize the tail of the distribution, that is, understand how many elements appear infrequently. We develop an algorithm based on a careful buck…
