Research map / Optimization / Nonconvex and smooth optimization
Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator
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 |
|---|---|---|---|
| SPIDER variance-reduced estimator added to Frank-Wolfe (SPIDER-FW) | Frank-Wolfe in non-convex finite-sum · non-convex finite-sum | ifo complexity | Helped |
| SPIDER variance-reduced estimator added to Frank-Wolfe (SPIDER-FW) | Frank-Wolfe in non-convex expectation minimization · non-convex expectation minimization | sfo complexity | Helped |
| SPIDER-FW matches SVRF-level ifo and lmo rates in convex finite-sum | Frank-Wolfe in convex finite-sum · convex finite-sum | ifo complexity | No clear effect |
| Conditional gradient sliding extended with SPIDER (SPIDER-CGS) versus SPIDER-FW | SPIDER-CGS · non-convex settings | oracle complexity | No clear effect |
| Using CGS in the non-convex setting instead of FW | Conditional gradient sliding · non-convex FW-gap | FW-gap oracle complexity | No clear effect |
Closest papers by meaning
- SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator (NeurIPS 2018 · similarity 0.91)
- Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization (ICML 2020 · similarity 0.90)
- Stochastic Frank-Wolfe for Composite Convex Minimization (NeurIPS 2019 · similarity 0.90)
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.90)
- Can Stochastic Zeroth-Order Frank-Wolfe Method Converge Faster for Non-Convex Problems? (ICML 2020 · similarity 0.89)
- Efficient Quadratic Corrections for Frank-Wolfe Algorithms (NeurIPS 2025 · similarity 0.86)
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.