Research map / Optimization / Nonconvex and smooth optimization
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
Kiran K Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
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 |
|---|---|---|---|
| combine Moreau-Yosida smoothing with accelerated gradient sliding | Nonsmooth convex optimization with a projection oracle · General nonsmooth convex optimization | FO calls: \Ord(\frac{(G^2+\sigma^2)\|x_0 - x^*\|^2}{\varepsilon^2}) | No clear effect |
| replace exact projections with Frank-Wolfe approximate projections | MOPES, yielding MOLES · General nonsmooth convex optimization | LMO calls: \Ord(\sqrt{d}\varepsilon^{-2}) -> \Ord({\frac{G^2 D_\mathcal{X}^2}{\varepsilon^2}}) | Improved |
| replace exact projections with Frank-Wolfe approximate projections | MOPES, yielding MOLES · General nonsmooth convex optimization | FO calls: \Ord(\frac{(G^2+\sigma^2)D_\mathcal{X}^2}{\varepsilon^2}) | No clear effect |
| use Moreau smoothing and ordinary accelerated gradient descent rather than joint optimization with gradient sliding (ablation) | Moreau envelope optimization · General nonsmooth convex optimization | FO calls: \Ord({\varepsilon^{-3}}) vs. \Ord({\varepsilon^{-2}}) | Hurt |
| use a generic approximate proximal step with error \delta=\varepsilon instead of Prox-Slide (ablation) | Inexact APGD · General nonsmooth convex optimization | FO calls: \Ord({G^3D_\mathcal{X}^3/\varepsilon^3}) vs. MOPES \Ord(\frac{(G^2+\sigma^2)\|x_0 - x^*\|^2}{\varepsilon^2}) | Hurt |
| use only the average of Prox-Slide iterates instead of the final iterate (ablation) | MOPES · General nonsmooth convex optimization | FO calls: increases by a factor of \Ord(\varepsilon^{-1}) | Hurt |
| use MOPES instead of PGD | Low-rank SVM on Imagewoof 2.0 · Imagewoof 2.0 low-rank SVM | PO calls | Improved |
| use MOLES instead of FW-PGD or RandFW | Low-rank SVM on Imagewoof 2.0 · Imagewoof 2.0 low-rank SVM | LMO calls | Improved |
Closest papers by meaning
- Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set (NeurIPS 2025 · similarity 0.90)
- A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates (ICML 2017 · similarity 0.89)
- Revisiting Projection-Free Optimization for Strongly Convex Constraint Sets (AAAI 2019 · similarity 0.89)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.88)
- Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization (ICML 2024 · similarity 0.87)
- First-Order Methods for Linearly Constrained Bilevel Optimization (NeurIPS 2024 · similarity 0.86)
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.
