Accelerated Frank-Wolfe Algorithms: Complementarity Conditions and Sparsity

arXiv:2511.02821 · math.OC, cs.LG · Submitted 2025-11-04 · Read on arXiv

math.OC, cs.LG

Submitted: 2025-11-04

Updated: 2026-09-08

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

Terminology

• Sparsity — 26× in this paper · explained in 4 episodes
• Ambient Dimension — 8× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• Trace — 4× in this paper · explained in 2 episodes
• Convergence Guarantees — 3× in this paper · explained in 3 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Accelerated Projection — 1× in this paper · explained in 1 episode
• Inverse Problem — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes

Sources

• $k$FW: A Frank-Wolfe style algorithm with stronger subproblem oracles
• A Randomized Linearly Convergent Frank-Wolfe-type Method for Smooth Convex Minimization over the Spectrahedron
• The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle

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