Research map / Optimization / Nonconvex and smooth optimization
Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization
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 |
|---|---|---|---|
| Use constant batch size stochastic Frank-Wolfe with per-sample dual update (one scalar per sample) instead of Mokhtari et al. (2018) estimator | Stochastic Frank-Wolfe (SFW) · BREAST CANCER, RCV1, CALIFORNIA HOUSING (l1-constrained) | relative suboptimality vs number of sampled gradients | Helped |
| Replace the averaged-iterate scheme of Lu & Freund (2018) with SFW's last-iterate updates | Stochastic Frank-Wolfe (SFW) · RCV1 and other l1 tasks | relative suboptimality vs number of sampled gradients | Helped |
| Stochastic Frank-Wolfe gap estimator used as stopping criterion | Stochastic Frank-Wolfe (SFW) · theory | distance to true FW gap | No clear effect |
| Use sparsity of data points to restrict per-iteration cost to support of datapoint (l1 ball) | Stochastic Frank-Wolfe (SFW) · sparse datasets | per-iteration cost | Helped |
Closest papers by meaning
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.95)
- Stochastic Frank-Wolfe for Composite Convex Minimization (NeurIPS 2019 · similarity 0.93)
- Variance-Reduced and Projection-Free Stochastic Optimization (ICML 2016 · similarity 0.92)
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noises (ICML 2026 · similarity 0.91)
- Beyond Short Steps in Frank-Wolfe Algorithms (ICLR 2026 · similarity 0.91)
- 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.