Research map / Optimization / Nonconvex and smooth optimization
Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity
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 variance reduction in Meta-Frank-Wolfe (ablation) | Meta-Frank-Wolfe · Continuous facility location, Jester | regret | Helped |
| Use variance reduction in One-Shot Frank-Wolfe (ablation) | One-Shot Frank-Wolfe · Continuous facility location, Jester | regret | Helped |
| Use variance reduction in Meta-Frank-Wolfe (ablation) | Meta-Frank-Wolfe · Topic summarization, Reuters-21578 | (1-1/e)-regret | Helped |
| Use variance reduction in One-Shot Frank-Wolfe (ablation) | One-Shot Frank-Wolfe · Topic summarization, Reuters-21578 | (1-1/e)-regret | Helped |
| Use variance reduction in Meta-Frank-Wolfe (ablation) | Meta-Frank-Wolfe · Stochastic cost network flow | stochastic regret | Helped |
| Use variance reduction in One-Shot Frank-Wolfe (ablation) | One-Shot Frank-Wolfe · Stochastic cost network flow | stochastic regret | Helped |
| Use variance reduction in Meta-Frank-Wolfe (ablation) | Meta-Frank-Wolfe · Online convex matrix completion | regret | Helped |
| Use projection-free Meta-Frank-Wolfe instead of projected gradient descent | Online convex matrix completion · Online convex matrix completion | computational time: five times | Helped |
| Use the continuous lifting method rather than the compared discrete algorithms | Online discrete submodular maximization · Discrete facility location, Jester | regret | Helped |
Closest papers by meaning
- Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization (ICLR 2024 · similarity 0.91)
- Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints (NeurIPS 2024 · similarity 0.90)
- Online Submodular Maximization via Online Convex Optimization (AAAI 2024 · similarity 0.90)
- Revisiting Projection-Free Online Learning with Time-Varying Constraints (AAAI 2025 · similarity 0.89)
- Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness (NeurIPS 2025 · similarity 0.89)
- Projection-Free Online Convex Optimization with Time-Varying Constraints (ICML 2024 · similarity 0.89)
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.