Paper ID: 2410.08449 • Published Oct 11, 2024
Finite Sample and Large Deviations Analysis of Stochastic Gradient Algorithm with Correlated Noise
George Yin, Vikram Krishnamurthy
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
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.