English
Related papers

Related papers: Approximation to stochastic variance reduced gradi…

200 papers

Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new results. (1) We show that constant SGD can be used as an…

Machine Learning · Statistics 2018-01-23 Stephan Mandt , Matthew D. Hoffman , David M. Blei

Causal optimal transport and adapted Wasserstein distance have applications in different fields from optimization to mathematical finance and machine learning. The goal of this article is to provide equivalent formulations of these concepts…

Probability · Mathematics 2024-07-01 Mathias Beiglböck , Susanne Pflügl , Stefan Schrott

Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables, offering expressive generative modeling while capturing hidden structure. We recast maximum-likelihood…

Machine Learning · Computer Science 2025-10-20 Shiqin Tang , Shuxin Zhuang , Rong Feng , Runsheng Yu , Hongzong Li , Youzhi Zhang

We develop the mathematical foundations of the stochastic modified equations (SME) framework for analyzing the dynamics of stochastic gradient algorithms, where the latter is approximated by a class of stochastic differential equations with…

Machine Learning · Computer Science 2018-11-06 Qianxiao Li , Cheng Tai , Weinan E

Application of the replica exchange (i.e., parallel tempering) technique to Langevin Monte Carlo algorithms, especially stochastic gradient Langevin dynamics (SGLD), has scored great success in non-convex learning problems, but one…

Numerical Analysis · Mathematics 2023-01-06 Guanxun Li , Guang Lin , Zecheng Zhang , Quan Zhou

We study first-order optimality conditions for constrained optimization in the Wasserstein space, whereby one seeks to minimize a real-valued function over the space of probability measures endowed with the Wasserstein distance. Our…

Optimization and Control · Mathematics 2025-03-03 Nicolas Lanzetti , Saverio Bolognani , Florian Dörfler

A new (unadjusted) Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and in Wasserstein distance is presented. All these are obtained in the context of sampling from a target distribution $\pi$ that has a density…

Statistics Theory · Mathematics 2019-10-18 Sotirios Sabanis , Ying Zhang

The computation of Wasserstein gradient direction is essential for posterior sampling problems and scientific computing. The approximation of the Wasserstein gradient with finite samples requires solving a variational problem. We study the…

Machine Learning · Computer Science 2022-05-27 Yifei Wang , Peng Chen , Mert Pilanci , Wuchen Li

Langevin dynamics has become a popular tool to simulate the Boltzmann equilibrium distribution. When the repartition of the Langevin equation involves the exact realization of the Ornstein-Uhlenbeck noise, in addition to the conventional…

Chemical Physics · Physics 2017-11-15 Dezhang Li , Xu Han , Yichen Chai , Cong Wang , Zifei Chen , Zhijun Zhang , Jian Liu , Jiushu Shao

We present a new method to sample conditioned trajectories of a system evolving under Langevin dynamics, based on Brownian bridges. The trajectories are conditioned to end at a certain point (or in a certain region) in space. The bridge…

Mathematical Physics · Physics 2022-08-17 Patrice Koehl , Henri Orland

Stochastic Gradient Langevin Dynamics (SGLD) ensures strong guarantees with regards to convergence in measure for sampling log-concave posterior distributions by adding noise to stochastic gradient iterates. Given the size of many practical…

Machine Learning · Computer Science 2020-06-15 Vyacheslav Kungurtsev , Bapi Chatterjee , Dan Alistarh

We develop generalization error bounds for stochastic gradient descent (SGD) with label noise in non-convex settings under uniform dissipativity and smoothness conditions. Under a suitable choice of semimetric, we establish a contraction in…

Machine Learning · Statistics 2023-11-02 Jung Eun Huh , Patrick Rebeschini

We study pathwise approximation of scalar stochastic differential equations at a single point. We provide the exact rate of convergence of the minimal errors that can be achieved by arbitrary numerical methods that are based (in a…

Probability · Mathematics 2007-05-23 Thomas Muller-Gronbach

We study the multivariate deconvolution problem of recovering the distribution of a signal from independent and identically distributed observations additively contaminated with random errors (noise) from a known distribution. For errors…

Statistics Theory · Mathematics 2023-09-28 Judith Rousseau , Catia Scricciolo

Langevin algorithms are gradient descent methods with additive noise. They have been used for decades in Markov chain Monte Carlo (MCMC) sampling, optimization, and learning. Their convergence properties for unconstrained non-convex…

Machine Learning · Computer Science 2020-12-23 Andrew Lamperski

We present a novel approach to approximate Gaussian and mixture-of-Gaussians filtering. Our method relies on a variational approximation via a gradient-flow representation. The gradient flow is derived from a Kullback--Leibler discrepancy…

Computation · Statistics 2023-06-21 Adrien Corenflos , Hany Abdulsamad

In stochastic quantisation, quantum mechanical expectation values are computed as averages over the time history of a stochastic process described by a Langevin equation. Complex stochastic quantisation, though theoretically not rigorously…

High Energy Physics - Lattice · Physics 2014-08-18 Amel Durakovic , Emil Cortes Andre , Anders Tranberg

Many complex systems, ranging from migrating cells to animal groups, exhibit stochastic dynamics described by the underdamped Langevin equation. Inferring such an equation of motion from experimental data can provide profound insight into…

Biological Physics · Physics 2026-04-17 David B. Brückner , Pierre Ronceray , Chase P. Broedersz

We consider the weak convergence of numerical methods for stochastic differential equations (SDEs). Weak convergence is usually expressed in terms of the convergence of expected values of test functions of the trajectories. Here we present…

Numerical Analysis · Mathematics 2009-11-28 Benoit Charbonneau , Yuriy Svyrydov , P. F. Tupper

We consider the constrained sampling problem where the goal is to sample from a target distribution on a constrained domain. We propose skew-reflected non-reversible Langevin dynamics (SRNLD), a continuous-time stochastic differential…

Machine Learning · Computer Science 2025-04-16 Hengrong Du , Qi Feng , Changwei Tu , Xiaoyu Wang , Lingjiong Zhu