A Distributed Strategy for Computing Proximity Operators

Abstract : Various recent iterative optimization methods require to compute the proximity operator of a sum of functions. We address this problem by proposing a new distributed algorithm for a sum of non-necessarily smooth convex functions composed with arbitrary linear operators. In our approach, each function is associated with a node of a graph, which communicates with its neighbors. Our algorithm relies on a primal-dual splitting strategy that avoids to invert any linear operator, thus making it suitable for processing high-dimensional datasets. The proposed algorithm has a wide array of applications in signal/image processing and machine learning and its convergence is established.
Document type :
Conference papers
Liste complète des métadonnées

Contributor : Emilie Chouzenoux <>
Submitted on : Thursday, September 29, 2016 - 1:41:43 AM
Last modification on : Thursday, July 5, 2018 - 2:45:57 PM


  • HAL Id : hal-01373644, version 1


Feriel Abboud, Emilie Chouzenoux, Jean-Christophe Pesquet, Jean-Hugues Chenot, Louis Laborelli. A Distributed Strategy for Computing Proximity Operators. Asilomar Conference on Signals, Systems, and Computers, Nov 2015, Asilomar, United States. In Proceedings of 50th Asilomar Conference on Signals, Systems, and Computers (ASILOMAR 2015), p. 396-400, 2015. 〈hal-01373644〉



Record views