Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex Minimization

Paper recorded by Signals 4 on 2026-10-30 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-30 on arXiv · recorded by Signals 4 on 2026-11-02

Category: cs.LG · 机器学习 · first seen 2026-11-02

Abstract

This work considers the design of stepsize schedules for stochastic gradient descent in smooth convex optimization. Throughout, we assume that gradient noise is conditionally zero-mean with bounded variance. Among problems with dimension $d\geq N+1$, we provide an exact worst-case analysis of the expected suboptimality of stochastic gradient descent's final iterate. Our analysis applies to any (po

Read on arXiv →