Research map / Optimization / Distributed and compressed
Talk Less, Work More: Communication-Efficient Decentralized Stochastic Approximation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a decentralized stochastic approximation method where each agent performs H local updates between communication rounds to reduce communication cost for cooperative fixed-point solving.
Problem
Decentralized stochastic approximation for fixed-point solving over mesh networks without a central server, where communication is the main bottleneck relative to cheap local updates.
Approach
Each agent performs H local updates before each communication round, trading frequent coordination for cheaper local computation to reduce communication cost.
Closest papers by meaning
- Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate (NeurIPS 2022 · similarity 0.89)
- Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization (AAAI 2024 · similarity 0.88)
- On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization (NeurIPS 2024 · similarity 0.87)
- Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks (ICML 2025 · similarity 0.87)
- Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks (NeurIPS 2024 · similarity 0.87)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 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.