Research map / Optimization / Nonconvex and smooth optimization
Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use SpecFW (k=4 eigenvectors, k > r*=3) instead of FW for rank-3 quadratic sensing | Spectral Frank-Wolfe · Quadratic sensing, n=600, k > r* | relative objective vs iterations and time | Helped |
| Set k=2 (less than r*=3) for SpecFW (ablation) | Spectral Frank-Wolfe · Quadratic sensing, n=600, k < r* | relative objective vs iterations | No clear effect |
| Set k=2 (less than r*=3) for G-BlockFW (ablation) | G-BlockFW · Quadratic sensing, n=600, k < r* | relative objective vs iterations | Hurt |
| Use classical FW (single eigenvector) on rank-3 solution | Frank-Wolfe · Quadratic sensing, rank r*=3 | convergence rate | Hurt |
Closest papers by meaning
- Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions (ICLR 2026 · similarity 0.90)
- Frank-Wolfe Beyond 1/t Convergence (NeurIPS 2026 · similarity 0.90)
- Efficient Quadratic Corrections for Frank-Wolfe Algorithms (NeurIPS 2025 · similarity 0.89)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.89)
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.88)
- Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities (NeurIPS 2024 · similarity 0.88)
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.