Work

Finite Sample and Large Deviations Analysis of Stochastic Gradient Algorithm with Correlated Noise

Year: 2024

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2410.08449

Authors: Yin, George, Krishnamurthy, Vikram

Institutions: University of Connecticut, Cornell University

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4403444233

Cites:

Cited by:

Related to: 10