English
Related papers

Related papers: A sharp uniform-in-time error estimate for Stochas…

200 papers

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we…

Machine Learning · Computer Science 2024-01-17 Ali Ramezani-Kebrya , Kimon Antonakopoulos , Volkan Cevher , Ashish Khisti , Ben Liang

In this article, we study the problem of sampling from distributions whose densities are not necessarily smooth nor logconcave. We propose a simple Langevin-based algorithm that does not rely on popular but computationally challenging…

Machine Learning · Statistics 2025-12-02 Tim Johnston , Iosif Lytras , Nikolaos Makras , Sotirios Sabanis

Diffusion generative models have emerged as powerful tools for producing synthetic data from an empirically observed distribution. A common approach involves simulating the time-reversal of an Ornstein-Uhlenbeck (OU) process initialized at…

Machine Learning · Statistics 2025-12-02 Valentin de Bortoli , Romuald Elie , Anna Kazeykina , Zhenjie Ren , Jiacheng Zhang

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

Machine Learning · Computer Science 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian

We introduce in this paper the numerical analysis of high order both in time and space Lagrange-Galerkin methods for the conservative formulation of the advection-diffusion equation. As time discretization scheme we consider the Backward…

Numerical Analysis · Mathematics 2024-01-05 Rodolfo Bermejo , Manuel Colera

Conventional wisdom in the sampling literature, backed by a popular diffusion scaling limit, suggests that the mixing time of the Metropolis-Adjusted Langevin Algorithm (MALA) scales as $O(d^{1/3})$, where $d$ is the dimension. However, the…

Statistics Theory · Mathematics 2020-12-24 Sinho Chewi , Chen Lu , Kwangjun Ahn , Xiang Cheng , Thibaut Le Gouic , Philippe Rigollet

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Unadjusted Langevin Algorithm (ULA),…

Computation · Statistics 2021-07-28 Dao Nguyen , Xin Dang , Yixin Chen

We study the problem of sampling from a distribution $p^*(x) \propto \exp\left(-U(x)\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconvex inside this ball.…

We quantify, uniformly over time and with high probability, the discrepancy between the predictions of a two-layer neural network trained by stochastic gradient descent (SGD) and their mean-field limit, for quadratic loss and ridge…

Neural and Evolutionary Computing · Computer Science 2026-03-03 Arnaud Guillin , Boris Nectoux , Paul Stos

In this paper, we study the problem of computing the effective diffusivity for particles moving in chaotic flows. Instead of solving a convection-diffusion type cell problem in the Eulerian formulation (arising from homogenization theory…

Numerical Analysis · Mathematics 2020-12-17 Zhongjian Wang , Jack Xin , Zhiwen Zhang

In this article, we consider the problem of sampling from a probability measure $\pi$ having a density on $\mathbb{R}^d$ known up to a normalizing constant, $x\mapsto \mathrm{e}^{-U(x)} / \int_{\mathbb{R}^d} \mathrm{e}^{-U(y)} \mathrm{d}…

Methodology · Statistics 2018-11-27 Nicolas Brosse , Alain Durmus , Éric Moulines , Sotirios Sabanis

We propose a stochastic approximation (SA) based method with randomization of samples for policy evaluation using the least squares temporal difference (LSTD) algorithm. Our proposed scheme is equivalent to running regular temporal…

Machine Learning · Computer Science 2020-01-27 L. A. Prashanth , Nathaniel Korda , Rémi Munos

We revisit the problem of sampling from a target distribution that has a smooth strongly log-concave density everywhere in $\mathbb R^p$. In this context, if no additional density information is available, the randomized midpoint…

Statistics Theory · Mathematics 2023-06-19 Lu Yu , Avetik Karagulyan , Arnak Dalalyan

Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models, from regression to neural networks. Given the recent practical focus on…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-06-25 Dan Alistarh , Christopher De Sa , Nikola Konstantinov

Stein Variational Gradient Descent (SVGD) is an important alternative to the Langevin-type algorithms for sampling from probability distributions of the form $\pi(x) \propto \exp(-V(x))$. In the existing theory of Langevin-type algorithms…

Statistics Theory · Mathematics 2022-06-02 Lukang Sun , Avetik Karagulyan , Peter Richtarik

We establish sample complexity guarantees for estimating the covariance matrix of a strongly log-concave smooth distribution using the unadjusted Langevin algorithm (ULA). We quantitatively compare our complexity estimates on single-chain…

Probability · Mathematics 2026-02-16 Shogo Nakakita

We provide convergence guarantees in Wasserstein distance for a variety of variance-reduction methods: SAGA Langevin diffusion, SVRG Langevin diffusion and control-variate underdamped Langevin diffusion. We analyze these methods under a…

Machine Learning · Statistics 2018-02-16 Niladri S. Chatterji , Nicolas Flammarion , Yi-An Ma , Peter L. Bartlett , Michael I. Jordan

When training deep neural networks, it is typically assumed that the training examples are uniformly difficult to learn. Or, to restate, it is assumed that the training error will be uniformly distributed across the training examples. Based…

Machine Learning · Computer Science 2015-10-09 Andrew J. R. Simpson

Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications and benefit from strong theoretical guarantees. Recently, methods inspired by statistical mechanics, in…

Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for…

Machine Learning · Statistics 2015-12-25 Chunyuan Li , Changyou Chen , David Carlson , Lawrence Carin