The Exact Time-Uniform Rate Frontier for Stochastic Gradient Descent on Smooth Convex Objectives

arXiv:2609.08537 · math.OC, cs.LG, stat.ML · Submitted 2026-09-08 · Read on arXiv

math.OC, cs.LG, stat.ML

Submitted: 2026-09-08

Updated: 2026-09-08

Comments: 28 pages, including appendix

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Stochastic Gradient Descent (SGD) — 1× in this paper · explained in 5 episodes

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Online Control via Counterfactual Tracking
• Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability
• Petrov-Galerkin operator inference with application to stability-encouraging identification