In this paper, we introduce DICOD, a convolutional sparse coding algorithm which builds shift invariant representations for long signals. This algorithm is designed to run in a distributed setting, with local message passing, making it communication efficient. It is based on coordinate descent and uses locally greedy updates which accelerate the resolution compared to greedy coordinate selection. We prove the convergence of this algorithm and highlight its computational speed-up which is super-linear in the number of cores used. We also provide empirical evidence for the acceleration properties of our algorithm compared to state-of-the-art methods.
Thomas Moreau (CMLA, ENS Paris-Saclay)
Laurent Oudre (Universite Paris 13)
Nicolas Vayatis (CMLA, ENS Paris Saclay)
Related Events (a corresponding poster, oral, or spotlight)
2018 Oral: DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding »
Thu Jul 12th 09:40 -- 09:50 AM Room A9