Research map / Optimization / Nonconvex and smooth optimization
Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search
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 |
|---|---|---|---|
| Replace pairwise FW with away-step FW plus line search (AFW-2) on general polytopes | FW for general polytopes · Least square over Q_k | convergence speed (gap vs steps) | Helped |
| Replace pairwise FW with away-step FW plus line search on binary kernel SVM | RC-Hull SVM · Breast-cancer, a1a, ijcnn1 | primal objective vs kernel evaluations | Helped |
| Use line search instead of pre-defined step size for AFW | AFW on SLPs · SVM and general polytope experiments | practical efficiency | Helped |
Closest papers by meaning
- Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes (NeurIPS 2016 · similarity 0.93)
- Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity (NeurIPS 2020 · similarity 0.91)
- Blended Conditonal Gradients (ICML 2019 · similarity 0.91)
- Frank-Wolfe with Subsampling Oracle (ICML 2018 · similarity 0.87)
- Efficient Quadratic Corrections for Frank-Wolfe Algorithms (NeurIPS 2025 · similarity 0.86)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.85)
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.