Research map / Optimization / Nonconvex and smooth optimization
Fast Projection Onto Convex Smooth Constraints
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 |
|---|---|---|---|
| Fast projection (primal-dual with cutting plane on dual and AGD inner solves) instead of IPM | projection onto few smooth constraints · Synthetic projection m=2, n from 10 to 12000 | run-time (s) | Mixed |
| Fast projection instead of IPM | kernel learning QCQP, doc-rna · m=3, n=4000 vs n=11000 | run-time (s) | Mixed |
| Fast projection instead of IPM at target accuracy 1e-6 | kernel learning QCQP, m=3, n=11000 · accuracy 1e-6 | run-time (s) | Helped |
| Tightening target accuracy from 1e-6 to 1e-8 for fast projection | Fast projection on kernel learning · m=3, n=11000 | run-time (s): 83.2 -> 1216.9 | Hurt |
| Fast projection instead of ADMM | synthetic projection m=2 · n=10 to 1000 | run-time (s) | Helped |
| Fast projection instead of SLSQP | synthetic projection m=2 · n=5000 | run-time (s) | Helped |
Closest papers by meaning
- A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates (ICML 2017 · similarity 0.91)
- Projection-Free Algorithms for Minimax Problems (ICML 2026 · similarity 0.91)
- Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set (NeurIPS 2025 · similarity 0.89)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.87)
- Projection-Free Online Convex Optimization with Time-Varying Constraints (ICML 2024 · similarity 0.87)
- A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle (ICML 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.