Paper ID | SPTM-4.5 | ||
Paper Title | DECENTRALIZED OPTIMIZATION OVER NOISY, RATE-CONSTRAINED NETWORKS: HOW WE AGREE BY TALKING ABOUT HOW WE DISAGREE | ||
Authors | Rajarshi Saha, Stanford University, United States; Stefano Rini, National Chiao Tung University, Taiwan; Milind Rao, Amazon Alexa, United States; Andrea Goldsmith, Princeton University, United States | ||
Session | SPTM-4: Estimation, Detection and Learning over Networks 2 | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation | Poster | ||
Topic | Signal Processing Theory and Methods: Signal Processing over Networks | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | In decentralized optimization, multiple nodes in a network collaborate to minimize the sum of their local loss functions. The information exchange between nodes required for the task is often limited by network connectivity. We consider a generalization of this setting, in which communication is further hindered by (i) a finite data-rate constraint on the signal transmitted by any node, and (ii) an additive noise corrupting the signal received by any node. We develop a novel algorithm for this scenario: Decentralized Lazy Mirror Descent with Differential Exchanges (DLMD-DiffEx), which guarantees convergence of the local estimates to the optimal solution under the given communication constraints. A salient feature of DLMD-DiffEx is the introduction of additional proxy variables that are maintained by the nodes to account for the disagreement in their estimates due to channel noise and data-rate constraints. We investigate the performance of DLMD-DiffEx both from a theoretical perspective as well as through numerical evaluations. |