Research map / Optimization / Nonconvex and smooth optimization
Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization
Aryan Mokhtari, Hamed Hassani, Amin Karbasi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| average stochastic gradients over time (SFW) instead of using a single mini-batch gradient | Mini-batch FW · Stochastic quadratic program (n = 5, sigma = 100) | suboptimality gap | Improved |
| use SFW with b = 1 instead of mini-batch FW with b = 100 | Mini-batch FW · Stochastic quadratic program (sigma = 300) | suboptimality gap | Improved |
| use SFW with b = 10 instead of mini-batch FW with b = 1000 | Mini-batch FW · Matrix completion (n = 200) | normalized error: 0.55 -> 0.25 | Improved |
| increase SFW batch size from 10 to 1000 (ablation) | SFW · Matrix completion (n = 200) | normalized error: 0.25 -> 2.3\times 10^{-3} | Improved |
| use growing batch size O(t^2) instead of SFW | SFW · Matrix completion (n = 200), per iteration | normalized error | Hurt |
| use SFW instead of growing-batch FW when comparing by samples processed | Growing-batch FW · Matrix completion (n = 200), per sample | normalized error | Improved |
| set averaging parameter rho_t = O(t^{-2/3}) instead of t^{-1/3}, t^{-1/2} or t^{-1} (ablation) | SFW · Matrix completion (n = 200) | convergence | Improved |
Closest papers by meaning
- Gradient Methods for Submodular Maximization (NeurIPS 2017 · similarity 0.93)
- Conditional gradient methods for stochastically constrained convex minimization (ICML 2020 · similarity 0.93)
- Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization (ICML 2019 · similarity 0.92)
- Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization (ICML 2022 · similarity 0.91)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.91)
- Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization (NeurIPS 2025 · similarity 0.90)
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.
