English
Related papers

Related papers: Steady-State Behavior of Constant-Stepsize Stochas…

200 papers

We present a framework for obtaining explicit bounds on the rate of convergence to equilibrium of a Markov chain on a general state space, with respect to both total variation and Wasserstein distances. For Wasserstein bounds, our main tool…

Statistics Theory · Mathematics 2011-02-28 Neal Madras , Deniz Sezer

We establish a general, non-asymptotic error analysis framework for understanding the effects of incremental approximations made by practical approaches for Bayesian sequential learning (BSL) on their long-term inference performance. Our…

Statistics Theory · Mathematics 2025-07-29 Liliang Wang , Alex A. Gorodetsky

The sub-Gaussian stable distribution is a heavy-tailed elliptically contoured law which has interesting applications in signal processing and financial mathematics. This work addresses the problem of feasible estimation of distributions. We…

Statistics Theory · Mathematics 2022-08-04 Taras Bodnar , Dmitry Otryakhin , Erik Thorsen

We introduce a general framework for nonlinear stochastic gradient descent (SGD) for the scenarios when gradient noise exhibits heavy tails. The proposed framework subsumes several popular nonlinearity choices, like clipped, normalized,…

Optimization and Control · Mathematics 2022-04-07 Dusan Jakovetic , Dragana Bajovic , Anit Kumar Sahu , Soummya Kar , Nemanja Milosevic , Dusan Stamenkovic

In this paper, we characterize the noise of stochastic gradients and analyze the noise-induced dynamics during training deep neural networks by gradient-based optimizers. Specifically, we firstly show that the stochastic gradient noise…

Machine Learning · Computer Science 2021-09-22 Yixin Wu , Rui Luo , Chen Zhang , Jun Wang , Yaodong Yang

We demonstrate that for strongly log-convex densities whose potentials are discontinuous on manifolds, the ULA algorithm converges with stepsize bias of order $1/2$ in Wasserstein-p distance. Our resulting bound is then of the same order as…

Probability · Mathematics 2023-12-05 Tim Johnston , Sotirios Sabanis

We present a framework that allows for the non-asymptotic study of the $2$-Wasserstein distance between the invariant distribution of an ergodic stochastic differential equation and the distribution of its numerical approximation in the…

Machine Learning · Statistics 2021-09-27 J. M. Sanz-Serna , Konstantinos C. Zygalakis

In the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus…

Machine Learning · Statistics 2021-06-14 Kangqiao Liu , Liu Ziyin , Masahito Ueda

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

In this work we study high probability bounds for stochastic subgradient methods under heavy tailed noise. In this setting the noise is only assumed to have finite variance as opposed to a sub-Gaussian distribution for which it is known…

Optimization and Control · Mathematics 2024-04-16 Daniela A. Parletta , Andrea Paudice , Massimiliano Pontil , Saverio Salzo

We study the behavior of the Wasserstein-$2$ distance between discrete measures $\mu$ and $\nu$ in $\mathbb{R}^d$ when both measures are smoothed by small amounts of Gaussian noise. This procedure, known as Gaussian-smoothed optimal…

Statistics Theory · Mathematics 2022-06-15 Yunzi Ding , Jonathan Niles-Weed

Cyclic and randomized stepsizes are widely used in the deep learning practice and can often outperform standard stepsize choices such as constant stepsize in SGD. Despite their empirical success, not much is currently known about when and…

Machine Learning · Statistics 2023-08-30 Mert Gürbüzbalaban , Yuanhan Hu , Umut Şimşekli , Lingjiong Zhu

Recent findings by Cohen et al., 2021, demonstrate that when training neural networks using full-batch gradient descent with a step size of $\eta$, the largest eigenvalue $\lambda_{\max}$ of the full-batch Hessian consistently stabilizes…

Machine Learning · Computer Science 2025-12-30 Arseniy Andreyev , Pierfrancesco Beneventano

Two-time-scale Stochastic Approximation (SA) is an iterative algorithm with applications in reinforcement learning and optimization. Prior finite time analysis of such algorithms has focused on fixed point iterations with mappings…

Machine Learning · Computer Science 2025-09-30 Siddharth Chandak , Shaan Ul Haque , Nicholas Bambos

We present a way to use Stein's method in order to bound the Wasserstein distance of order $2$ between two measures $\nu$ and $\mu$ supported on $\mathbb{R}^d$ such that $\mu$ is the reversible measure of a diffusion process. In order to…

Probability · Mathematics 2018-06-25 Thomas Bonis

Constant step-size Stochastic Gradient Descent exhibits two phases: a transient phase during which iterates make fast progress towards the optimum, followed by a stationary phase during which iterates oscillate around the optimal point. In…

Machine Learning · Computer Science 2020-07-02 Scott Pesme , Aymeric Dieuleveut , Nicolas Flammarion

We study Stochastic Gradient Descent with AdaGrad stepsizes: a popular adaptive (self-tuning) method for first-order stochastic optimization. Despite being well studied, existing analyses of this method suffer from various shortcomings:…

Machine Learning · Computer Science 2023-06-13 Amit Attia , Tomer Koren

The smooth 1-Wasserstein distance (SWD) $W_1^\sigma$ was recently proposed as a means to mitigate the curse of dimensionality in empirical approximation while preserving the Wasserstein structure. Indeed, SWD exhibits parametric convergence…

Statistics Theory · Mathematics 2022-02-28 Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

In this paper we propose tight upper and lower bounds for the Wasserstein distance between any two {{univariate continuous distributions}} with probability densities $p_1$ and $p_2$ having nested supports. These explicit bounds are…

Probability · Mathematics 2015-10-21 Christophe Ley , Gesine Reinert , Yvik Swan

Several issues in machine learning and inverse problems require to generate discrete data, as if sampled from a model probability distribution. A common way to do so relies on the construction of a uniform probability distribution over a…

Optimization and Control · Mathematics 2021-06-16 Quentin Merigot , Filippo Santambrogio , Clément Sarrazin