Research map / Optimization / Nonconvex and smooth optimization
A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization
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 LCPP with a proximal objective and gradually relaxed convex surrogate constraints | Nonconvex sparse constrained optimization · Nonconvex sparse learning problems | convergence guarantee: O(1/\varepsilon) | Helped |
| Use LCPP for stochastic or nonsmooth objectives | Nonconvex sparse constrained optimization · Stochastic or nonsmooth objectives | convergence guarantee: O(1/\varepsilon^2) | Helped |
| Use LCPP instead of DCCP with MOSEK | Classification · mnist, real-sim, rcv1.binary, gisette | objective value versus running time | Helped |
| Use the nonconvex sparse constrained model instead of Lasso-type regularization | Sparse learning models · mnist, real-sim, rcv1.binary, gisette, YearPredictionMSD, E2006 | testing error | Helped |
| Use MCP-based nonconvex models rather than Lasso across sparsity levels | Sparse learning models · Classification and regression datasets | testing error robustness across sparsity levels | Helped |
| Use spectral gradient descent to solve LCPP subproblems instead of the other tested first-order solvers | LCPP subproblem solver · Logistic regression | solver performance | Helped |
Closest papers by meaning
- On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning (NeurIPS 2017 · similarity 0.91)
- Projective Proximal Gradient Descent for Nonconvex Nonsmooth Optimization: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property (ICLR 2023 · similarity 0.90)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · similarity 0.88)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.88)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.87)
- Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization (ICML 2024 · similarity 0.87)
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.