Research map / Optimization / Distributed and compressed
Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks
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 |
|---|---|---|---|
| Use multi-step Chebyshev-accelerated gossip rather than one gossip step per iteration (ablation) | Dual accelerated decentralized optimization · Strongly convex and smooth decentralized optimization | time to precision ε: O((1+τ)√(κ_l/γ)ln(1/ε)) -> O(√κ_l(1+τ/√γ)ln(1/ε)) | Helped |
| Use MSDA instead of SSDA (ablation) | Decentralized optimization · Least-squares regression and logistic classification on the tested networks | convergence rate | Helped |
| Use DAGD rather than a decentralized method | Distributed optimization · Least-squares regression on the tested networks | convergence rate | Helped |
| Use MSDA rather than DAGD | Distributed optimization · Logistic classification on the tested networks | convergence rate | Helped |
| Use SSDA rather than D-ADMM | Logistic classification · 10×10 grid | iterations to reach the same error: 383 -> 10 | Helped |
Closest papers by meaning
- Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization (NeurIPS 2020 · similarity 0.93)
- Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks (NeurIPS 2021 · similarity 0.92)
- Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication (ICML 2019 · similarity 0.91)
- Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks (NeurIPS 2024 · similarity 0.91)
- Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization (AAAI 2024 · similarity 0.90)
- Towards Faster Decentralized Stochastic Optimization with Communication Compression (ICLR 2025 · 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.