Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks

Liyuan Liang; Xinyi Chen; Gan Luo; Kun Yuan

2025 ICML ICML 2025

Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Liyuan Liang, Xinyi Chen, Gan Luo, Kun Yuan

Topics

Machine Learning > Optimization & Theory > Optimization Mathematics & Optimization > Optimization > Continuous Optimization Mathematics & Optimization > Optimization > Stochastic Methods

Keywords

decentralized optimization gradient tracking convergence lower bound multi-step gossip pull-diag protocol row-stochastic networks

Download PDF