Research map / Optimization / Nonconvex and smooth optimization
Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization
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 |
|---|---|---|---|
| Replace the v1-SG estimator with the v1-SVRG estimator (ablation) | DEEPSTORM · a9a | test accuracy: 84.96±1235.0e-4 -> 84.94±929.04e-4 | No clear effect |
| Use the v2 estimator instead of v1-SG (ablation) | DEEPSTORM · a9a | test accuracy: 84.96±1235.0e-4 -> 85.11±478.03e-4 | No clear effect |
| Replace the v1-SG estimator with the v1-SVRG estimator (ablation) | DEEPSTORM · MiniBooNE | test accuracy: 84.24±1902.0e-4 -> 84.15±1974.0e-4 | No clear effect |
| Use the v2 estimator instead of v1-SG (ablation) | DEEPSTORM · MiniBooNE | test accuracy: 84.24±1902.0e-4 -> 84.25±1752.0e-4 | No clear effect |
| Replace the v1-SG estimator with the v1-SVRG estimator (ablation) | DEEPSTORM · MNIST | test accuracy: 97.97±1261.0e-4 -> 98.08±1485.0e-4 | No clear effect |
| Use the v2 estimator instead of v1-SG (ablation) | DEEPSTORM · MNIST | test accuracy: 97.97±1261.0e-4 -> 98.15±659.04e-4 | No clear effect |
| Use DEEPSTORM v1-SG instead of DSGT | DEEPSTORM · a9a | test accuracy: 84.89±271.02e-4 -> 84.96±1235.0e-4 | No clear effect |
| Use DEEPSTORM v1-SG instead of DSGT | DEEPSTORM · MiniBooNE | test accuracy: 84.24±202.07e-4 -> 84.24±1902.0e-4 | No clear effect |
| Use DEEPSTORM v1-SG instead of DSGT | DEEPSTORM · MNIST | test accuracy: 97.61±1346.0e-4 -> 97.97±1261.0e-4 | No clear effect |
Closest papers by meaning
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.88)
- Decentralized Projected Riemannian Stochastic Recursive Momentum Method for Nonconvex Optimization (AAAI 2025 · similarity 0.87)
- Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization (AAAI 2024 · similarity 0.86)
- Decentralized Sum-of-Nonconvex Optimization (AAAI 2024 · similarity 0.86)
- Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations (ICML 2024 · similarity 0.86)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 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.