Research map / Optimization / Nonconvex and smooth optimization
SCOPE: Scalable Composite Optimization for Learning on Spark
Shen-Yi Zhao, Ru Xiang, Ying-Hao Shi, Peng Gao, Wu-Jun Li
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 |
|---|---|---|---|
| Add the proximal correction term controlled by c (c=10 in the example) (ablation) | SCOPE · Impact of c example | convergence | Improved |
| Set c to 0 (ablation) | SCOPE · Impact of c example | convergence | Hurt |
| Set c to 1 or 5 (ablation) | SCOPE · Impact of c example | convergence | No clear effect |
| Use local stochastic optimization and communicate at outer iterations rather than each inner step | SCOPE · MNIST-8M | training efficiency | Improved |
| Use SCOPE instead of SVRGfoR | SCOPE · KDD12 | training efficiency | Improved |
| Use SCOPE instead of the evaluated Spark baselines | SCOPE · MNIST-8M, epsilon, KDD12, and Data-A | training efficiency | Improved |
Closest papers by meaning
- Distributed Stochastic Optimization via Adaptive SGD (NeurIPS 2018 · similarity 0.88)
- Distributed Stochastic Nested Optimization for Emerging Machine Learning Models: Algorithm and Theory (AAAI 2023 · similarity 0.86)
- Distributed Submodular Maximization (JMLR 2016 · similarity 0.86)
- Proximal SCOPE for Distributed Sparse Learning (NeurIPS 2018 · similarity 0.85)
- Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning (NeurIPS 2022 · similarity 0.85)
- Asynchronous Distributed Semi-Stochastic Gradient Optimization (AAAI 2016 · similarity 0.85)
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.
