TR-SSQP: A Trust-Region Method for Constrained Stochastic Optimization under Heavy-Tailed Noise

arXiv:2609.30732 · math.OC, cs.LG, stat.CO, stat.ML · Submitted 2026-09-25 · Read on arXiv

math.OC, cs.LG, stat.CO, stat.ML

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Accuracy — 7× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Convergence Guarantees — 4× in this paper · explained in 3 episodes
• Objective Function — 4× in this paper · explained in 2 episodes
• Lyapunov function — 3× in this paper · explained in 2 episodes
• Adaptive Sampling — 2× in this paper · explained in 1 episode
• Robustness — 2× in this paper · explained in 5 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Sample Complexity — 1× in this paper · explained in 15 episodes
• Stochastic Gradient Descent (SGD) — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• An Adaptive Sampling Sequential Quadratic Programming Method for Equality Constrained Stochastic Optimization
• Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models
• Why is Normalization Preferred? A Worst-Case Complexity Theory for Stochastically Preconditioned SGD under Heavy-Tailed Noise
• A Trust-Region Interior-Point Stochastic Sequential Quadratic Programming Method
• Online Inference of Constrained Optimization: Primal-Dual Optimality and Sequential Quadratic Programming
• The Power of Normalization: Faster Evasion of Saddle Points

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