Signals 4 · free daily AI digest

Improved Gradient Descent Lower Bounds Beyond Nesterov

Paper recorded by Signals 4 on 2026-09-02 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-02 on arXiv · recorded by Signals 4 on 2026-09-03

Category: cs.LG · 机器学习 · first seen 2026-09-03

Abstract

We study how far gradient descent (GD) can be accelerated by predetermined stepsizes in smooth convex optimization. Going beyond the classical $Ω(n^{-2})$ first-order oracle lower bound of Nemirovsky and Yudin, we prove an $Ω(n^{-1.6342})$ non-anytime lower bound and an $Ω(n^{-1.2408})$ anytime lower bound. These improve the recent $Ω(n^{-1.932})$ non-anytime lower bound of Ma and Chen and the $Ω(

Read on arXiv →

#145 most recent of 215 cs.LG papers we have recorded · ↑ newer: GRADSOLVE: fast exact gradients for ODE ensembles on GPUs · ↓ older: The Implications of Linguistic Illegibility for LLM Security
Cite this page: Improved Gradient Descent Lower Bounds Beyond Nesterov: the #145 most recent of 215 cs.LG papers we have recorded (as of 2026-09-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/improved-gradient-descent-lower-bounds-beyond-nesterov.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions