OFF Newton-type Methods for Unconstrained Optimization with Inexact Derivatives

arXiv:2512.06825 · math.OC · Submitted 2025-12-07 · Read on arXiv

math.OC

Submitted: 2025-12-07

Updated: 2026-10-22

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Adaptive sampling strategy — 1× in this paper · explained in 2 episodes
• Objective Function — 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