Research map / Optimization / Distributed and compressed
Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis
Dachao Lin, Yuze Han, Haishan Ye, Zhihua Zhang
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 AccSVRS rather than Catalyzed SVRP | Distributed optimization under AveSS · Strongly convex objective under AveSS | communication complexity: Catalyzed SVRP includes a \log\frac{L}{\mu} factor; AccSVRS does not | Improved |
| Lower the strong-convexity parameter in the synthetic ridge-regression experiments | SVRS and AccSVRS · Synthetic ridge regression | function gap | Mixed |
| Use a fixed local proximal function f1 rather than changing the proximal function with the sampled client | SVRS · Distributed optimization under AveSS | component strong-convexity requirement | Improved |
Closest papers by meaning
- Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity (NeurIPS 2024 · similarity 0.93)
- Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement (JMLR 2017 · similarity 0.91)
- Optimal Convergence Rates for Convex Distributed Optimization in Networks (JMLR 2019 · similarity 0.91)
- Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity (AAAI 2025 · similarity 0.90)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.90)
- Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits (NeurIPS 2026 · similarity 0.89)
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.
