Research map / Optimization / Nonconvex and smooth optimization
Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming
Daoli Zhu, Lei Zhao
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 |
|---|---|---|---|
| randomized block-coordinate updates (RPDC) instead of updating all blocks each iteration (APP-AL) | SVM problem with heart scale and ionosphere scale datasets · SVM (heart scale, ionosphere scale) | total iterations to reach suboptimality/feasibility | Improved |
| randomized block-coordinate updates (RPDC) instead of updating all blocks each iteration (APP-AL) | SVM problem · SVM (heart scale, ionosphere scale) | average computation time per iteration | Improved |
| randomized coordinate descent (RCD) baseline replacing the primal-dual scheme | SVM problem · SVM (heart scale, ionosphere scale) | total iterations to convergence | Hurt |
| linear convergence under global strong metric subregularity of the KKT mapping | RPDC on SVM and MLP problems · SVM and MLP | convergence rate | Improved |
Closest papers by meaning
- On the Complexity Analysis of the Primal Solutions for the Accelerated Randomized Dual Coordinate Ascent (JMLR 2020 · similarity 0.89)
- Random extrapolation for primal-dual coordinate descent (ICML 2020 · similarity 0.88)
- Linear Convergence of Randomized Feasible Descent Methods Under the Weak Strong Convexity Assumption (JMLR 2016 · similarity 0.88)
- Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization (JMLR 2017 · similarity 0.88)
- Faster Randomized Interior Point Methods for Tall/Wide Linear Programs (JMLR 2022 · similarity 0.87)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · 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.
