跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24151 · v1

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

首次提交 2026-11-18 17:55
版本更新 2026-11-18 17:55
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

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−1/3k^{-1/3} when a stationary minimizer exists, and k−1/4k^{-1/4} otherwise, up to polylogarithmic factors, where kk 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 −1/3-1/3 and −1/4-1/4 are optimal, up to polylogarithmic factors, for the corresponding problem classes.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 17:55 · 最新观测版本

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

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−1/3k^{-1/3} when a stationary minimizer exists, and k−1/4k^{-1/4} otherwise, up to polylogarithmic factors, where kk 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 −1/3-1/3 and −1/4-1/4 are optimal, up to polylogarithmic factors, for the corresponding problem classes.

查看此版本解读 →查看此版本原文 ↗