Research map / Learning theory and algorithms / Matrix and tensor methods
Coordinate Linear Variance Reduction for Generalized Linear Programming
Chaobing Song, Cheuk Yin Lin, Stephen Wright, Jelena Diakonikolas
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 |
|---|---|---|---|
| Use CLVR instead of production LP solvers | Wasserstein DRO LP reformulation · Reformulated gisette | time to accuracy 10^-8 (seconds): 1039.7 -> 697 | Improved |
| Use CLVR instead of production LP solvers | Wasserstein DRO LP reformulation · Reformulated rcv1 | time to accuracy 10^-8 (seconds): 1039.5 -> 582 | Improved |
| Use CLVR instead of Gurobi barrier | Wasserstein DRO LP reformulation · Reformulated a9a | time to accuracy 10^-8 (seconds): 26 -> 962 | Hurt |
| Use CLVR instead of primal-dual baselines | Wasserstein DRO LP reformulation · a9a, gisette, and rcv1 | wall-clock time | Improved |
| Use CLVR with block size 1 | CLVR · a9a, gisette, and rcv1 | number of data passes | Improved |
| Increase CLVR block size from 1 to 10 | CLVR · a9a, gisette, and rcv1 | number of data passes | Hurt |
| Use CLVR with block size 10 instead of block size 1 | CLVR · Wasserstein DRO LP reformulation | wall-clock time | Improved |
| Use CLVR instead of GLPK or Gurobi simplex | Wasserstein DRO LP reformulation · Reformulated gisette and rcv1 | time to accuracy 10^-8 (seconds): 2482 -> 697; 7008 -> 582 | Improved |
Closest papers by meaning
- Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems (ICML 2020 · similarity 0.86)
- Scalable First-order Method for Certifying Optimal k-Sparse GLMs (ICML 2025 · similarity 0.86)
- Learning Generalized Linear Programming Value Functions (NeurIPS 2024 · similarity 0.86)
- Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient (ICML 2024 · similarity 0.86)
- Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming (ICML 2020 · similarity 0.85)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.84)
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.
