Research map / Optimization / Nonconvex and smooth optimization
Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes
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 |
|---|---|---|---|
| decomposition-invariant away-steps (no explicit convex decomposition maintained) | pairwise CG on structured polytopes · theory | memory and per-iteration overhead | Helped |
| replace dimension-dependent rate factor with card(x*) | pairwise CG with DICG away-steps · theory (sparse optimum) | iterations to epsilon error | Helped |
| DICG versus ACG/PCG in video co-localization (flow polytope) | DICG · video co-localization | duality gap vs iterations | Helped |
| DICG versus PCG on Lasso (simplex-equivalent) | DICG · Lasso | duality gap vs iterations | No clear effect |
| DICG versus ACG/PCG on OCR | DICG · OCR structured SVM | running time | Helped |
Closest papers by meaning
- Blended Conditonal Gradients (ICML 2019 · similarity 0.93)
- Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search (NeurIPS 2017 · similarity 0.93)
- Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity (NeurIPS 2020 · similarity 0.91)
- Reusing Combinatorial Structure: Faster Iterative Projections over Submodular Base Polytopes (NeurIPS 2021 · similarity 0.89)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.88)
- Efficient Quadratic Corrections for Frank-Wolfe Algorithms (NeurIPS 2025 · 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.