A Unifying Perspective on Descent Directions for Constrained Minimization and Switching Criteria
math.OC, cs.LG
Submitted: 2020-06-15
Updated: 2026-10-02
Code: https://github.com/hassanmortagy/Walking-in-the-Shadow
Sources
- The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle
- Polytope conditioning and linear convergence of the Frank-Wolfe algorithm
- Boosting Frank-Wolfe by Chasing Gradients
- Blended Conditional Gradients: the unconditioning of conditional gradients
- Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application
- A unifying framework for the analysis of projection-free first-order methods under a sufficient slope condition
- Solving relaxations of MAP-MRF problems: Combinatorial in-face Frank-Wolfe directions
- First-order (coarse) correlated equilibria in non-concave games
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
- Second-Order Optimization with Asynchronous Curvature
- Online Control via Counterfactual Tracking
- Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability