The Last Iterate of the Projected Stochastic Subgradient Method Pays a Logarithm, Even in Dimension One
math.OC
Submitted: 2026-07-31
Updated: 2026-07-31
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