Work

Nearly Tight Almost Sure Convergence Rates for the Last iterate of SGD

Year: 2026
Type: preprint
Abstract: We study the almost sure convergence of the last-iterate optimization error of Stochastic (sub)Gradient Descent (SGD) for convex objectives. For smooth objectives, we establish convergence rates of order $k^{-1/3}$ when a stationary minimizer exists, and $k^{-1/4}$ otherwise, up to polylogarithmic factors, where $k$ denotes the iteration counter. We further show that the latter rate extends to nonsmooth convex objectives. All these rates are achieved by deterministic, anytime stepsize policies. Finally, we establish matching lower bounds showing that the exponents $-1/3$ and $-1/4$ are optimal, up to polylogarithmic factors, for the corresponding problem classes.
Language: English
Open Access status: green
OpenAlex ID: W7236809731
Cites: 35
Cited by:
Related to: 10