Perturbed Gradient Descent Algorithms are Small-Disturbance Input-to-State Stable

arXiv:2507.02131 · math.OC, cs.SY, eess.SY · Submitted 2025-07-02 · Read on arXiv

math.OC, cs.SY, eess.SY

Submitted: 2025-07-02

Updated: 2026-10-27

Terminology

• Objective Function — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 6 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
• 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