math.OC · 2026-06-24 · No. 33
Optimization and Control, 2026-06-24.
1 new papers in math.OC. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
New Bounds for the Last Iterate of the Stochastic subGradient Method
Guglielmo Beretta, Tommaso Cesari, Roberto Colomboni, Andrea Paudice
math.OC · cs.LG
We study the last iterate of the stochastic subgradient method for one-dimensional convex Lipschitz objectives. For a fixed horizon $n$, we consider the standard fixed stepsizes $η=Θ(1/\sqrt n)$. We prove that, for such stepsize policies, under additive i.i.d. subgradient noise with uniformly bounded variance, the last iterate features an optimization error of order $1/\sqrt n$, thereby removing the extra $(\log n)$ factor present in existing...
This edition is part of The Daily Abstract — math.OC archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.