Research map / Learning theory and algorithms / Matrix and tensor methods
On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning
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 |
|---|---|---|---|
| Replace first-order inner solver (proximal gradient / coordinate descent) with DC proximal Newton | multistage convex relaxation for nonconvex sparse logistic regression · simulated and real datasets (Table 1) | wall clock time (s) | Helped |
| Use DC proximal Newton instead of DC proximal gradient (APG) | DC multistage relaxation · gisette | wall clock time (s): 5.35s vs 207s | Helped |
| Use DC proximal Newton instead of DC proximal gradient (APG) | DC multistage relaxation · sim_10k | wall clock time (s): 8.82s vs 222s | Helped |
| Use DC proximal Newton instead of DC coordinate descent (ACD) | DC multistage relaxation · madelon | wall clock time (s): 1.51s vs 5.83s | Helped |
| Use DC proximal Newton on madelon versus DC proximal gradient (APG) | DC multistage relaxation · madelon | wall clock time (s): 1.51s vs 1.60s | No clear effect |
| Use DC proximal Newton instead of DC coordinate descent (ACD) at larger dimension | DC multistage relaxation · sim_10k | wall clock time (s): 8.82s vs 19.1s; advantage shrinks as d grows | Mixed |
Closest papers by meaning
- A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization (NeurIPS 2020 · similarity 0.91)
- An Alternating Proximal Splitting Method with Global Convergence for Nonconvex Structured Sparsity Optimization (AAAI 2016 · similarity 0.90)
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.88)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.86)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.86)
- Adaptive Proximal Gradient Method for Convex 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.