Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Push-Pull with Device Sampling

Abstract : We consider decentralized optimization problems in which a number of agents collaborate to minimize the average of their local functions by exchanging over an underlying communication graph. Specifically, we place ourselves in an asynchronous model where only a random portion of nodes perform computation at each iteration, while the information exchange can be conducted between all the nodes and in an asymmetric fashion. For this setting, we propose an algorithm that combines gradient tracking and variance reduction over the entire network. This enables each node to track the average of the gradients of the objective functions. Our theoretical analysis shows that the algorithm converges linearly, when the local objective functions are strongly convex, under mild connectivity conditions on the expected mixing matrices. In particular, our result does not require the mixing matrices to be doubly stochastic. In the experiments, we investigate a broadcast mechanism that transmits information from computing nodes to their neighbors, and confirm the linear convergence of our method on both synthetic and real-world datasets.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03691122
Contributor : Yu-Guan HSIEH Connect in order to contact the contributor
Submitted on : Wednesday, June 8, 2022 - 8:26:49 PM
Last modification on : Saturday, July 23, 2022 - 3:36:04 AM

File

Decentralized_optim.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03691122, version 1

Citation

Yu-Guan Hsieh, Yassine Laguel, Franck Iutzeler, Jérôme Malick. Push-Pull with Device Sampling. 2022. ⟨hal-03691122⟩

Share

Metrics

Record views

37

Files downloads

5