Anytime-Feasible Gradient Descent for Constrained Optimization Under Gradient Uncertainty

arXiv:2609.23848 · math.OC, cs.SY, eess.SY · Submitted 2026-09-20 · Read on arXiv

math.OC, cs.SY, eess.SY

Submitted: 2026-09-20

Updated: 2026-09-20

Terminology

• Gradient Flow — 3× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sequential Quadratic Programming — 1× in this paper

Sources

• Anytime-Feasible First-Order Optimization via Safe Sequential QCQP
• Off-Policy Reinforcement Learning with Anytime Safety Guarantees via Robust Safe Gradient Flow
• On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems

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