Research map / Optimization / Nonconvex and smooth optimization
Asynchronous Proximal Stochastic Gradient Algorithm for Composition Optimization Problems
Pengfei Wang, Risheng Liu, Nenggan Zheng, Zhefeng Gong
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 |
|---|---|---|---|
| increase number of threads to 16 | Async-ProxSCVR · MDP and mean-variance composition optimization, 16 threads | running time speedup: about 12 speedup on 16 threads | Improved |
| increase number of threads (objective vs time) | Async-ProxSCVR · MDPs and mean-variance problems | objective vs running time | Improved |
| increase number of threads (objective vs iterations) | Async-ProxSCVR · MDPs and mean-variance problems | objective vs iterations | No clear effect |
| use Async-ProxSCVR instead of HOGWILD!, Async-ProxSVRG, ASC-PG, com-SVR-ADMM | Async-ProxSCVR · MDPs (100 states, 3 actions), MDPs (400 states, 10 actions), mean-variance N=2000 and N=5000 | objective vs running time | Improved |
| increase threads from 1 to 8 to 16 in comparison with baselines | Async-ProxSCVR vs baselines · four composition problems | robustness to thread count | Improved |
Closest papers by meaning
- Accelerating Stochastic Composition Optimization (NeurIPS 2016 · similarity 0.92)
- Accelerated Method for Stochastic Composition Optimization With Nonsmooth Regularization (AAAI 2018 · similarity 0.89)
- Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization (AAAI 2024 · similarity 0.87)
- Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms (ICML 2024 · similarity 0.87)
- A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization (ICML 2025 · similarity 0.87)
- Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization (NeurIPS 2024 · 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.
