Convergence of Markov Chains for Constant Step-Size Stochastic Gradient Descent with Separable Functions

David Shirokoff; Philip Zaleski

doi:10.1137/24m1694598

ScienceGate Book Chapters

JOURNAL ARTICLE

Convergence of Markov Chains for Constant Step-Size Stochastic Gradient Descent with Separable Functions

David Shirokoff Philip Zaleski

Year: 2025 Journal: SIAM Journal on Applied Dynamical Systems Vol: 24 (3)Pages: 2005-2043 Publisher: Society for Industrial and Applied Mathematics

DOI: 10.1137/24m1694598

Get Full-Text PDF Get Analytical Report

Keywords:

Markov chain Constant (computer programming) Convergence (economics) Separable space Applied mathematics Gradient descent Mathematics Stochastic gradient descent Computer science Statistical physics Mathematical analysis Physics Statistics Artificial intelligence Artificial neural network Economics

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.20

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Markov Chains and Monte Carlo Methods

Physical Sciences → Mathematics → Statistics and Probability

Stochastic Gradient Optimization Techniques

Physical Sciences → Computer Science → Artificial Intelligence

Random Matrices and Applications

Physical Sciences → Mathematics → Statistics and Probability

Convergence of Markov Chains for Constant Step-Size Stochastic Gradient Descent with Separable Functions

Metrics

Topics

Related Documents

Bridging the gap between constant step size stochastic gradient descent and Markov chains

Convergence rate of stochastic gradient with constant step size

Convergence of Constant Step Stochastic Gradient Descent for Non-Smooth Non-Convex Functions

Modified Step Size for Enhanced Stochastic Gradient Descent: Convergence and Experiments

Stochastic Gradient Descent with Preconditioned Polyak Step-Size