Research map / Optimization / Nonconvex and smooth optimization
Blended Conditonal Gradients
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 |
|---|---|---|---|
| Blending CG steps, lazy weak-separation steps, and simplex gradient descent steps (BCG) instead of away/pairwise steps | conditional gradient for smooth convex minimization over polytopes · Four test problems (Figure 1) | iterations and wall-clock time to reach target function value | Helped |
| Linear convergence guarantee for strongly convex functions via simplicial curvature and geometric strong convexity | BCG · Theory (Theorem 3.1) | iteration complexity | No clear effect |
| Sparse-iterate property from aggressive reuse of active vertices | BCG · Sparse signal recovery, Lasso, structured regression, video co-localization | number of vertices in final convex combination | Helped |
Closest papers by meaning
- Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity (NeurIPS 2020 · similarity 0.93)
- Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes (NeurIPS 2016 · similarity 0.93)
- Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search (NeurIPS 2017 · similarity 0.91)
- Stochastic Frank-Wolfe for Composite Convex Minimization (NeurIPS 2019 · similarity 0.90)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.89)
- Efficient Quadratic Corrections for Frank-Wolfe Algorithms (NeurIPS 2025 · 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.