English
Related papers

Related papers: On the stability of the stochastic gradient Langev…

200 papers

This article suggests that deterministic Gradient Descent, which does not use any stochastic gradient approximation, can still exhibit stochastic behaviors. In particular, it shows that if the objective function exhibit multiscale…

Machine Learning · Computer Science 2020-11-03 Lingkai Kong , Molei Tao

Stochastic-approximation gradient methods are attractive for large-scale convex optimization because they offer inexpensive iterations. They are especially popular in data-fitting and machine-learning applications where the data arrives in…

Optimization and Control · Mathematics 2014-01-09 Michael P. Friedlander , Gabriel Goh

This paper considers the problem of learning, from samples, the dependency structure of a system of linear stochastic differential equations, when some of the variables are latent. In particular, we observe the time evolution of some…

Machine Learning · Computer Science 2012-05-02 Ali Jalali , Sujay Sanghavi

Sampling from discrete distributions is a ubiquitous task in machine learning, recently revisited by the emergence of discrete diffusion models. While Langevin algorithms constitute the state of the art for continuous spaces, discrete…

Statistics Theory · Mathematics 2026-02-18 Armand Gissler , Saeed Saremi , Francis Bach

We provide a framework to analyze the convergence of discretized kinetic Langevin dynamics for $M$-$\nabla$Lipschitz, $m$-convex potentials. Our approach gives convergence rates of $\mathcal{O}(m/M)$, with explicit stepsize restrictions,…

Numerical Analysis · Mathematics 2024-05-24 Benedict Leimkuhler , Daniel Paulin , Peter A. Whalley

A wide body of work has applied the concept of critical slowing down to estimate the stability of different Earth system components. Most of them -- such as global vegetation -- are inherently non-stationary, for example due to strong…

Chaotic Dynamics · Physics 2026-04-28 Taylor Smith , Andreas Morr , Christof Schötz , Niklas Boers

In this paper we address the problem of consistently construct Langevin equations to describe fluctuations in non-linear systems. Detailed balance severely restricts the choice of the random force, but we prove that this property together…

Condensed Matter · Physics 2007-05-23 J. Bonet Avalos , I. Pagonabarraga

Non-Markovian stochastic Langevin-like equations of motion are compared to their corresponding Markovian (local) approximations. The validity of the local approximation for these equations, when contrasted with the fully nonlocal ones, is…

Statistical Mechanics · Physics 2009-12-23 R. L. S. Farias , Rudnei O. Ramos , L. A. da Silva

We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Tiffany Vlaar , Timothée Pouchon , Amos Storkey

The so-called SAGA-LD algorithm is used for efficient sampling from high-dimensional distributions in machine learning. Its intricate dynamics resists standard approaches of Markov chain theory. We prove, using a model-specific method, that…

Probability · Mathematics 2026-04-15 Miklós Rásonyi

We rigorously show that a local spin system giving rise to a slow Hamiltonian dynamics is stable against generic, even time-dependent, local perturbations. The sum of these perturbations can cover a significant amount of the system's size.…

Quantum Physics · Physics 2024-11-12 Daniele Toniolo , Sougato Bose

We describe a criterion for particles suspended in a randomly moving fluid to aggregate. Aggregation occurs when the expectation value of a random variable is negative. This random variable evolves under a stochastic differential equation.…

Statistical Mechanics · Physics 2009-11-10 B. Mehlig , M. Wilkinson , K. Duncan , T. Weber , M. Ljunggren

The classical convergence analysis of SGD is carried out under the assumption that the norm of the stochastic gradient is uniformly bounded. While this might hold for some loss functions, it is violated for cases where the objective…

Optimization and Control · Mathematics 2019-11-12 Lam M. Nguyen , Phuong Ha Nguyen , Peter Richtárik , Katya Scheinberg , Martin Takáč , Marten van Dijk

We revisit processes generated by iterated random functions driven by a stationary and ergodic sequence. Such a process is called strongly stable if a random initialization exists, for which the process is stationary and ergodic, and for…

Probability · Mathematics 2024-02-06 László Györfi , Attila Lovas , Miklós Rásonyi

We consider variational inequality solutions with prescribed gradient constraints for first order linear boundary value problems. For operators with coefficients only in $L^2$, we show the existence and uniqueness of the solution by using a…

Analysis of PDEs · Mathematics 2015-02-04 José Francisco Rodrigues , Lisa Santos

Constrained sampling is an important and challenging task in computational statistics, concerned with generating samples from a distribution under certain constraints. There are numerous types of algorithm aimed at this task, ranging from…

Methodology · Statistics 2026-04-01 Neil K. Chada , Lu Yu

This note provides a simple derivation of the overdamped approximation for kinetic (or underdamped) equilibrium Langevin dynamics, in cases where certain coefficients depend on the position variable. The equivalent small-mass limit of these…

Probability · Mathematics 2026-05-11 Noé Blassel

In this paper, we prove convergence in distribution of Langevin processes in the overdamped asymptotics. The proof relies on the classical perturbed test function (or corrector) method, which is used both to show tightness in path space,…

Probability · Mathematics 2019-03-11 Mathias Rousset , Yushun Xu , Pierre-André Zitt

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex…

Machine Learning · Computer Science 2023-01-13 Tomer Koren , Roi Livni , Yishay Mansour , Uri Sherman

Linear response theory is a fundamental framework studying the macroscopic response of a physical system to an external perturbation. This paper focuses on the rigorous mathematical justification of linear response theory for Langevin…

Analysis of PDEs · Mathematics 2024-08-27 Yuan Gao , Jian-Guo Liu , Zibu Liu
‹ Prev 1 8 9 10 Next ›