The Exponential Price of Determinism in Nonsmooth Nonconvex Optimization

arXiv:2609.23837 · math.OC, cs.LG · Submitted 2026-09-20 · Read on arXiv

math.OC, cs.LG

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: 13 pages

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

Terminology

• Adam — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Curse of Dimensionality — 2× in this paper · explained in 6 episodes
• Sample Complexity — 1× in this paper · explained in 15 episodes

Sources

• On computing Goldstein approximate second-order stationary points of structured nonsmooth nonconvex programs
• Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization
• Nonsmooth Nonconvex-Concave Minimax Optimization: Convergence Criteria and Algorithms

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