Research map / Optimization / Optimizers
Approximate Steepest Coordinate Descent
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 ASCD instead of UCD for coordinate selection | Coordinate descent · Synthetic least squares and Lasso; RCV1-binary training | objective convergence | Helped |
| Initialize ASCD with arbitrary gradient estimates instead of the true gradient (ablation) | ASCD · Synthetic data and RCV1-binary training | objective convergence | No clear effect |
| Use the crude g4 gradient oracle instead of more precise, more expensive oracles (ablation) | ASCD · RCV1-binary training | objective convergence | No clear effect |
| Use heuristic a-ASCD active-set selection instead of the standard ASCD active set (ablation) | ASCD · Synthetic data and RCV1-binary training | objective convergence | No clear effect |
Closest papers by meaning
- Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling (ICML 2016 · similarity 0.89)
- When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent (NeurIPS 2017 · similarity 0.89)
- Accelerated Stochastic Greedy Coordinate Descent by Soft Thresholding Projection onto Simplex (NeurIPS 2017 · similarity 0.88)
- Accelerating Greedy Coordinate Descent Methods (ICML 2018 · similarity 0.88)
- Stochastic Spectral and Conjugate Descent Methods (NeurIPS 2018 · similarity 0.87)
- Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent (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.