Automated Performance Estimation for Decentralized Optimization via Network Size Independent Problems

Author name not available (Why is that?)

Publication date: 2 October 2022

Abstract: We develop a novel formulation of the Performance Estimation Problem (PEP) for decentralized optimization whose size is independent of the number of agents in the network. The PEP approach allows computing automatically the worst-case performance and worst-case instance of first-order optimization methods by solving an SDP. Unlike previous work, the size of our new PEP formulation is independent of the network size. For this purpose, we take a global view of the decentralized problem and we also decouple the consensus subspace and its orthogonal complement. We apply our methodology to different decentralized methods such as DGD, DIGing and EXTRA and obtain numerically tight performance guarantees that are valid for any network size.

Has companion code repository: https://github.com/sebcolla/performance-estimation-problems-for-distributed-optimization

This page was built for publication: Automated Performance Estimation for Decentralized Optimization via Network Size Independent Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6412694)