Local LMO is Secretly a Projection Method!

arXiv:2609.33383 · math.OC, cs.LG · Submitted 2026-09-27 · Read on arXiv

math.OC, cs.LG

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

• Objective Function — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Admissibility — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Convergence Guarantees — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Hilbert Space — 1× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 1× in this paper
• International Conference on Machine Learning — 1× in this paper

Sources

• Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge
• Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
• The Ball-Proximal (="Broximal") Point Method: a New Algorithm, Convergence Theory, and Applications
• A Linearly Convergent Projection-Free Algorithm for Smooth Convex Sets
• Revisiting the Polyak step size
• New Results on the Polyak Stepsize: Tight Convergence Analysis and Universal Function Classes
• The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle
• Deep Neural Network Training with Frank-Wolfe
• Broximal Gradient Descent: A Projection-Free Sister of Projected Gradient Descent
• Stability of Constrained Optimization Models for Structured Signal Recovery

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