Research map / Optimization / Nonconvex and smooth optimization
Stochastic Frank-Wolfe for Composite Convex 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 homotopy smoothing with a decreasing smoothing parameter for affine constraints | SHCGM · Stochastic convex composite minimization with affine constraints | feasibility gap: \mathcal{O}(k^{-5/12}) | Helped |
| Use a single-sample stochastic gradient estimator with gradient averaging | SHCGM · Stochastic convex composite minimization | sample complexity: \mathcal{O}({1}/{\varepsilon^{3}}) vs. \mathcal{O}({1}/{\varepsilon^{4}}) | Helped |
| Apply SFW without the hard rating-bound constraint | SFW · MovieLens100k | training and test RMSE | Hurt |
| Replace projection-based optimization with SHCGM | MovieLens-1M comparison against S3CCM · MovieLens-1M | iterations in two hours: 27'860 vs. 435 | Helped |
| Use SHCGM instead of deterministic HCGM with a full-data gradient | Stochastic k-means clustering SDP · MNIST k-means clustering SDP | objective performance | No clear effect |
| Use online stochastic samples instead of a fixed batch | Covariance matrix estimation · Online covariance matrix estimation | objective residual convergence rate: \mathcal{O}(k^{-1/2}) | Helped |
Closest papers by meaning
- Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization (ICML 2020 · similarity 0.93)
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.92)
- Can Stochastic Zeroth-Order Frank-Wolfe Method Converge Faster for Non-Convex Problems? (ICML 2020 · similarity 0.92)
- Efficient Quadratic Corrections for Frank-Wolfe Algorithms (NeurIPS 2025 · similarity 0.88)
- Frank-Wolfe Beyond 1/t Convergence (NeurIPS 2026 · similarity 0.88)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (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.