D-FW: Communication efficient distributed algorithms for high-dimensional sparse optimization

Abstract : We propose distributed algorithms for high-dimensional sparse optimization. In many applications, the parameter is sparse but high-dimensional. This is pathological for existing distributed algorithms as the latter require an information exchange stage involving transmission of the full parameter, which may not be sparse during the intermediate steps of optimization. The novelty of this work is to develop communication efficient algorithms using the stochastic Frank-Wolfe (sFW) algorithm, where the gradient computation is inexact but controllable. For star network topology, we propose an algorithm with low communication cost and establishes its convergence. The proposed algorithm is then extended to perform decentralized optimization on general network topology. Numerical experiments are conducted to verify our findings.
Document type :
Conference papers
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-01419048
Contributor : Eric Moulines <>
Submitted on : Monday, December 19, 2016 - 8:09:09 PM
Last modification on : Thursday, October 17, 2019 - 12:36:09 PM

Identifiers

Citation

Jean Lafond, Hoi-To Wai, Éric Moulines. D-FW: Communication efficient distributed algorithms for high-dimensional sparse optimization. International Conference on Acoustics, Speech and Signal Processing , Mar 2016, Shangai, China. pp.4144 - 4148, ⟨10.1109/ICASSP.2016.7472457⟩. ⟨hal-01419048⟩

Share

Metrics

Record views

564