Research map / Optimization / Nonconvex and smooth optimization
Can Stochastic Zeroth-Order Frank-Wolfe Method Converge Faster for Non-Convex Problems?
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 ZSCG's averaged Gaussian gradient estimator with coordinate-wise estimator plus variance reduction (FZFW) | zeroth-order Frank-Wolfe · Synthetic MCCR (Syn-1, Syn-2) | objective value vs iterations | Helped |
| Add conditional gradient sliding (acceleration) to FZFW (FZCGS) (ablation) | zeroth-order Frank-Wolfe · Synthetic MCCR (Syn-1, Syn-2) | objective value vs iterations | Helped |
| Add conditional gradient sliding (acceleration) to FZFW (FZCGS) (ablation) | zeroth-order Frank-Wolfe · Low-rank matrix completion (MovieLens100k) | loss value vs iterations | Helped |
| Add conditional gradient sliding (acceleration) to FZFW (FZCGS) (ablation) | zeroth-order Frank-Wolfe · Adversarial examples on black-box DNN (MNIST) | objective value vs iterations | Helped |
| Use variance-reduced first-order conditional gradient sliding (FCGS) instead of NCGS-VR | first-order conditional gradient sliding · Synthetic MCCR (Syn-1, Syn-2) | objective value vs number of function queries | Helped |
Closest papers by meaning
- Accelerated Stochastic Gradient-free and Projection-free Methods (ICML 2020 · similarity 0.93)
- Stochastic Frank-Wolfe for Composite Convex Minimization (NeurIPS 2019 · similarity 0.92)
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.91)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.89)
- Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization (ICML 2024 · similarity 0.89)
- Frank-Wolfe Beyond 1/t Convergence (NeurIPS 2026 · 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.