A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training

arXiv:2605.14860 · math.OC, cs.LG · Submitted 2026-05-14 · Read on arXiv

math.OC, cs.LG

Submitted: 2026-05-14

Updated: 2026-05-14

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Building on the Additively Preconditioned Trust-Region Strategy — 1× in this paper
• Preconditioner — 1× in this paper · explained in 2 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