Research map / Optimization / Nonconvex and smooth optimization
On Frank-Wolfe and Equilibrium Computation
Jacob D. Abernethy, Jun-Kun Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Cumulative-gradient linear oracle (Algorithm 3) instead of last-gradient oracle in Frank-Wolfe | Frank-Wolfe · smooth convex constrained optimization (theoretical) | approximation error rate | No clear effect |
| Stochastic smoothing of objective via random perturbation (FTPL-style, as in Mokhtari et al.) | Frank-Wolfe on non-smooth objectives · constrained convex optimization (theoretical) | approximation error rate | No clear effect |
| Boundary Frank-Wolfe: swap roles so x-player is prescient, using FTL on strongly convex decision set, no smoothness of f required | Frank-Wolfe on non-smooth objectives over strongly convex sets · strongly convex constraint set (theoretical) | convergence rate | Improved |
| Adding random perturbation (Gaussian-like) to gradient in boundary FW to guarantee nonzero cumulative gradient | Boundary Frank-Wolfe · strongly convex constraint set (theoretical) | convergence rate | Hurt |
Closest papers by meaning
- Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities (NeurIPS 2024 · similarity 0.90)
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.89)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.88)
- Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points (NeurIPS 2026 · similarity 0.87)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.87)
- Efficient Learning in Polyhedral Games via Best-Response Oracles (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
