Gradient descent reaches arbitrary accuracy in a fixed number of large steps on multiclass logistic regression

arXiv:2610.26748 · math.OC, cs.LG · Submitted 2026-10-19 · Read on arXiv

math.OC, cs.LG

Submitted: 2026-10-19

Updated: 2026-10-19

Comments: 40 pages

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

Terminology

• Accuracy — 1× in this paper · explained in 1 episode

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
• Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning
• Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets
• Second-Order Optimization with Asynchronous Curvature