Research map / Optimization / Nonconvex and smooth optimization
Geometric Descent Method for Convex Composite Minimization
Shixiang Chen, Shiqian Ma, Wei Liu
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 GeoPG-B instead of APG-B | Linear regression with elastic net · Ill-conditioned synthetic problem, p=4000 n=2000, α=10^{-6}, μ=1.136e-02 | CPU time (seconds): 4.9 -> 0.7 | Improved |
| Use GeoPG-B instead of APG-B | Linear regression with elastic net · a9a, α=10^{-6}, λ=1e-03 | CPU time (seconds): 10.4 -> 0.9 | Improved |
| Use GeoPG-B instead of APG-B | Linear regression with elastic net · RCV1, α=10^{-8}, λ=1e-03 | CPU time (seconds): 4.2 -> 1.0 | Improved |
| Use GeoPG-B instead of APG-B | Linear regression with elastic net · Gisette, α=10^{-4}, μ=1e-03 | CPU time (seconds): 1504.2 -> 342.4 | Improved |
| Add limited-memory ball intersections (ablation) | GeoPG-B · Gisette logistic regression | performance | Improved |
| Use GeoPG-B rather than APG-B on well-posed problems | Elastic-net regression · Well-posed problems, such as α = 0.01 | CPU time (seconds) | Hurt |
Closest papers by meaning
- On Acceleration for Convex Composite Minimization with Noise-Corrupted Gradients and Approximate Proximal Mapping (JMLR 2022 · similarity 0.88)
- Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization (NeurIPS 2023 · similarity 0.88)
- Extensions to the Proximal Distance Method of Constrained Optimization (JMLR 2022 · similarity 0.87)
- A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization (TPAMI 2021 · similarity 0.87)
- Non-convex Stochastic Composite Optimization with Polyak Momentum (ICML 2024 · similarity 0.87)
- Adaptive Proximal Gradient Method for Convex Optimization (NeurIPS 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.
