Research map / Optimization / Nonconvex and smooth optimization
Accelerating Greedy Coordinate Descent Methods
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 |
|---|---|---|---|
| greedy coordinate selection in accelerated framework (AGCD) instead of random coordinate (ARCD) | accelerated coordinate descent on linear regression · synthetic linear regression, Figure 1 | optimality gap vs run-time | Helped |
| semi-greedy x-update with random z-update (ASCD) instead of random coordinate (ARCD) | accelerated coordinate descent on linear regression · synthetic linear regression, Figure 1 | optimality gap vs run-time | Helped |
| greedy coordinate selection (AGCD) instead of random (ARCD) | accelerated coordinate descent on logistic regression · LIBSVM w1a, a1a | optimality gap vs run-time | Helped |
| semi-greedy ASCD instead of ARCD with small assumed strong convexity mu | accelerated coordinate descent on logistic regression · LIBSVM w1a, a1a | optimality gap vs run-time | Mixed |
| ASCD greedy x-update with random z-update, theoretical O(1/k^2) guarantee | ASCD non-strongly convex · theory (Theorem 2.1) | E[f(x_k)-f*] bound | Helped |
| Technical Condition 4.1 (gamma<1) assumed for AGCD | AGCD · LIBSVM datasets, Table 1 | observed gamma | No clear effect |
Closest papers by meaning
- Accelerated Stochastic Greedy Coordinate Descent by Soft Thresholding Projection onto Simplex (NeurIPS 2017 · similarity 0.91)
- First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems (ICML 2019 · similarity 0.90)
- Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints (NeurIPS 2024 · similarity 0.88)
- Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares (ICML 2024 · similarity 0.88)
- Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad Generalization (ICLR 2025 · similarity 0.87)
- Fundamental Benefit of Alternating Updates in Minimax Optimization (ICML 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.