Research map / Optimization / Nonconvex and smooth optimization
Towards An Efficient Approach for the Nonconvex lp Ball Projection: Algorithm and Analysis
Xiangyu Yang, Jiashan Wang, Hao Wang
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 |
|---|---|---|---|
| use IRBP instead of the root-searching (RS) method | lp ball projection · n=100, p=0.4 | success rate: about 25% -> all instances | Improved |
| use IRBP instead of the root-searching (RS) method | lp ball projection · n=100, p=0.8 | success rate: about 70% -> all instances | Improved |
| use IRBP instead of RS for wall-clock time | lp ball projection · n=100, p in {0.4, 0.8} | elapsed time: IRBP less than 0.1s for p=0.4 and 0.01s for p=0.8 | Improved |
| scale IRBP to n up to 10^6 where RS fails within the time limit | IRBP · n in {1e3,1e4,1e5,1e6}, p in {0.4,0.8} | solvability | Improved |
| vary M from 10 to 10^4 and tau from 1.01 to 1.8 (ablation) | IRBP · p=0.5, n=1e5 | objective value and time: Obj 157.956 to 158.322; Time 16.97 to 17.70 | No clear effect |
Closest papers by meaning
- Compact Convex Projections (JMLR 2018 · similarity 0.85)
- Inexact Newton-type Methods for Optimisation with Nonnegativity Constraints (ICML 2024 · similarity 0.84)
- Semismooth Newton Algorithm for Efficient Projections onto $\ell_1, ∞$-norm Ball (ICML 2020 · similarity 0.84)
- Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data (ICML 2023 · similarity 0.84)
- Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming (NeurIPS 2024 · similarity 0.83)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.83)
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.
