English
Related papers

Related papers: A weak convergence approach to large deviations fo…

200 papers

This paper focuses on systems of nonlinear second-order stochastic differential equations with multi-scales. The motivation for our study stems from mathematical physics and statistical mechanics, for examples, Langevin dynamics and…

Probability · Mathematics 2024-04-08 Nhu N. Nguyen , George Yin

The work concerns deviation estimates for multivalued McKean-Vlasov stochastic differential equations. First of all, we prove the large deviation principle for them by the weak convergence approach. Then the central limit theorem for them…

Probability · Mathematics 2022-08-10 Kun Fang , Huijie Qiao

This study focuses on large deviation principles for fully coupled multiscale multivalued stochastic systems, in which the slow component is governed by a multivalued stochastic differential equation and the fast component is described by a…

Probability · Mathematics 2025-12-12 Huijie Qiao

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

The tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error rather than generalizable theory. We address this theory--practice gap by characterizing the large-sample…

Computation · Statistics 2023-07-21 Jeffrey Negrea , Jun Yang , Haoyue Feng , Daniel M. Roy , Jonathan H. Huggins

Large-scale optimization problems require algorithms both effective and efficient. One such popular and proven algorithm is Stochastic Gradient Descent which uses first-order gradient information to solve these problems. This paper studies…

Optimization and Control · Mathematics 2021-11-11 Theodoros Mamalis , Dusan Stipanovic , Petros Voulgaris

We consider potential type dynamical systems in finite dimensions with two meta-stable states. They are subject to two sources of perturbation: a slow external periodic perturbation of period $T$ and a small Gaussian random perturbation of…

Probability · Mathematics 2007-05-23 Samuel Herrmann , Peter Imkeller , Dierk Peithmann

In this paper we establish the large deviation principle for the stochastic quasi-geostrophic equation in the subcritical case with small multiplicative noise. The proof is mainly based on the stochastic control and weak convergence…

Probability · Mathematics 2013-05-22 Wei Liu , Michael Röckner , Xiangchan Zhu

We propose a computational method for large deviation statistics of time-averaged quantities in general Markov processes. In our proposed method, we repeat a response measurement against external forces, where the forces are determined by…

Statistical Mechanics · Physics 2014-03-12 Takahiro Nemoto , Shin-ichi Sasa

We study large deviations in the context of stochastic gradient descent for one-hidden-layer neural networks with quadratic loss. We derive a quenched large deviation principle, where we condition on an initial weight measure, and an…

Probability · Mathematics 2025-01-14 Christian Hirsch , Daniel Willhalm

This paper is concerned with the large deviation principle of the non-local fractional stochastic reaction-diffusion equation with a polynomial drift of arbitrary degree driven by multiplicative noise defined on unbounded domains. We first…

Probability · Mathematics 2023-05-23 Bixiang Wang

Motivated by learning of correlated equilibria in non-cooperative games, we perform a large deviations analysis of a regret minimizing stochastic approximation algorithm. The regret minimization algorithm we consider comprises multiple…

Optimization and Control · Mathematics 2024-06-04 Hongjiang Qian , Vikram Krishnamurthy

Using the weak convergence approach, we prove the large deviation principle (LDP) for solutions to quasilinear stochastic evolution equations with small Gaussian noise in the critical variational setting, a recently developed general…

Probability · Mathematics 2026-02-23 Esmée Theewis , Mark Veraar

The Freidlin-Wentzell large deviation principle is established for the distributions of stochastic evolution equations with general monotone drift and small multiplicative noise. As examples, the main results are applied to derive the large…

Probability · Mathematics 2010-05-06 Wei Liu

Many machine learning and optimization algorithms are built upon the framework of stochastic approximation (SA), for which the selection of step-size (or learning rate) $\{\alpha_n\}$ is crucial for success. An essential condition for…

Statistics Theory · Mathematics 2025-08-05 Caio Kalil Lauand , Sean Meyn

This paper establishes the first almost sure convergence rate and the first maximal concentration bound with exponential tails for general contractive stochastic approximation algorithms with Markovian noise. As a corollary, we also obtain…

Machine Learning · Computer Science 2024-11-22 Xiaochi Qian , Zixuan Xie , Xinyu Liu , Shangtong Zhang

The ODE method has been a workhorse for algorithm design and analysis since the introduction of the stochastic approximation. It is now understood that convergence theory amounts to establishing robustness of Euler approximations for ODEs,…

Optimization and Control · Mathematics 2020-10-02 Shuhang Chen , Adithya Devraj , Andrey Bernstein , Sean Meyn

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

In this paper, we establish a large deviation principle for the stochastic generalized Ginzburg-Landau equation driven by jump noise. The main difficulties come from the highly non-linear coefficient. Here we adopt a new sufficient…

Probability · Mathematics 2021-11-17 Ran Wang , Beibei Zhang

Stochastic gradient descent is one of the most successful approaches for solving large-scale problems, especially in machine learning and statistics. At each iteration, it employs an unbiased estimator of the full gradient computed from one…

Numerical Analysis · Mathematics 2018-12-05 Bangti Jin , Xiliang Lu