Research map / Optimization / Nonconvex and smooth optimization
Coordinate Descent Methods for DC Minimization: Optimality Conditions and Global Convergence
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 sequential nonconvex approximation rather than sequential convex approximation (ablation) | Coordinate descent for DC minimization · ℓ1 norm generalized eigenvalue problem, randn-256-1024 | objective value: -1.426 $\pm$ 0.056 -> -1.447 $\pm$ 0.053 | Helped |
| Use sequential nonconvex approximation rather than sequential convex approximation (ablation) | Coordinate descent for approximate sparse optimization · randn-256-1024 | objective value: 0.092 $\pm$ 0.018 -> 0.034 $\pm$ 0.004 | Helped |
| Use CD-SNCA instead of MSCR | ℓ1 norm generalized eigenvalue problem · randn-256-1024 | objective value: -1.329 $\pm$ 0.038 -> -1.447 $\pm$ 0.053 | Helped |
Closest papers by meaning
- Coordinate Descent Methods for Fractional Minimization (ICML 2023 · similarity 0.91)
- Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence (ICML 2019 · similarity 0.90)
- When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent (NeurIPS 2017 · similarity 0.89)
- Discrete and Continuous Difference of Submodular Minimization (ICML 2025 · similarity 0.87)
- Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning (AAAI 2025 · similarity 0.87)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 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.