Finite Sample and Large Deviations Analysis of Stochastic Gradient Algorithm with Correlated Noise
Machine Learning
2024-10-14 v1 Systems and Control
Systems and Control
Abstract
We analyze the finite sample regret of a decreasing step size stochastic gradient algorithm. We assume correlated noise and use a perturbed Lyapunov function as a systematic approach for the analysis. Finally we analyze the escape time of the iterates using large deviations theory.
Cite
@article{arxiv.2410.08449,
title = {Finite Sample and Large Deviations Analysis of Stochastic Gradient Algorithm with Correlated Noise},
author = {George Yin and Vikram Krishnamurthy},
journal= {arXiv preprint arXiv:2410.08449},
year = {2024}
}