Research map / Optimization / Nonconvex and smooth optimization
Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex 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 a homotopy schedule for the smoothing parameter instead of a fixed smoothing parameter | SMART-CD · General three-composite convex template | convergence complexity: \mathcal{O}(n^2/k) -> \mathcal{O}(n/k) | Helped |
| Add restart to SMART-CD | SMART-CD · Linear SVM with bias | duality gap convergence | Helped |
| Add restart to SMART-CD | SMART-CD · Degenerate linear program | convergence | No clear effect |
| Use SMART-CD rather than Vu-Condat-CD | Coordinate descent on the degenerate linear program · Degenerate linear program (p=10, d=200) | primal suboptimality convergence | Helped |
| Apply SDCA without the equality constraint required by the SVM with bias | SDCA · Linear SVM with bias | duality gap convergence | Hurt |
| Use coordinate descent rather than full-dimensional methods | SMART-CD and Vu-Condat-CD · fMRI TV-ℓ1-regularized least squares | convergence in time | Helped |
Closest papers by meaning
- Random extrapolation for primal-dual coordinate descent (ICML 2020 · similarity 0.91)
- First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems (ICML 2019 · similarity 0.89)
- Accelerating Greedy Coordinate Descent Methods (ICML 2018 · similarity 0.89)
- Solving Non-smooth Constrained Programs with Lower Complexity than $\mathcal{O}(1/\varepsilon)$: A Primal-Dual Homotopy Smoothing Approach (NeurIPS 2018 · similarity 0.89)
- Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimization (ICML 2023 · similarity 0.89)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · 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.