Research map / Optimization / Nonconvex and smooth optimization
MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC-regularized Optimization
Luxuan Li, Chunfeng Cui, Xiao 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 single-loop MoSSP-P instead of double-loop SPDC-P | DC-regularized logistic regression with unit-sphere constraint · a9a | constraint violation: 3.23 × 10−2 -> 1.53 × 10−3 | Improved |
| use single-loop MoSSP-P instead of double-loop SALM-P | DC-regularized logistic regression with unit-sphere constraint · a9a | constraint violation: 1.30 × 10−2 -> 1.53 × 10−3 | Improved |
| use MoSSP-R instead of SALM-R | DC-regularized logistic regression with unit-sphere constraint · a9a | objective value: 0.6303 -> 0.5809 | Improved |
| use MoSSP-P instead of SPDC-P | DC-regularized logistic regression · phishing | objective value: 0.6051 -> 0.6045 | No clear effect |
| use MoSSP-P instead of SPDC-P | DC-regularized logistic regression · australian | constraint violation: 1.95 × 10−3 -> 7.14 × 10−3 | Hurt |
| use MoSSP-R instead of SPDC-R | DC-regularized logistic regression · australian | constraint violation: 1.94 × 10−3 -> 6.88 × 10−3 | Hurt |
| use MoSSP-R instead of SPDC-R | DC-regularized logistic regression · phishing | constraint violation: 1.10 × 10−1 -> 4.63 × 10−3 | Improved |
| add DC structure (nonsmooth concave part) to constrained stochastic penalty method | MoSSP · theory | oracle complexity order | No clear effect |
Closest papers by meaning
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · similarity 0.89)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.89)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.88)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.88)
- Non-convex Stochastic Composite Optimization with Polyak Momentum (ICML 2024 · similarity 0.88)
- Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization (ICML 2024 · similarity 0.88)
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.
