Research map / Optimization / Nonconvex and smooth optimization
Three Operator Splitting with a Nonconvex Loss Function
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 TOS instead of Frank-Wolfe to solve the relaxed QAP over the Birkhoff polytope before rounding | QAP relax-and-round · QAPLIB (134 instances) | assignment error: TOS better on 83, FW better on 35, tie on 16; average margin 0.046 | Helped |
| TOS with step-size 1/Lf instead of the theoretical T-dependent step-size | TOS on nonconvex QAP · QAP relaxed problem (chr12a, esc128) | convergence behavior | Helped |
| TOS vs FW convergence on relaxed QAP | TOS · QAP relaxed problem (chr12a, esc128) | convergence rate | Helped |
Closest papers by meaning
- Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization (ICML 2024 · similarity 0.85)
- Non-geodesically-convex optimization in the Wasserstein space (NeurIPS 2024 · similarity 0.84)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.84)
- Stochastic Optimization with Random Search (NeurIPS 2026 · similarity 0.84)
- Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations (ICML 2025 · similarity 0.84)
- ADMM for Nonconvex Optimization under Minimal Continuity Assumption (ICLR 2025 · similarity 0.84)
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.