Home » Publication » 19634

Dettaglio pubblicazione

2019, JOURNAL OF MACHINE LEARNING RESEARCH, Pages 1-62 (volume: 20)

Decentralized Dictionary Learning Over Time-Varying Digraphs (01a Articolo in rivista)

Daneshmand Amir, Sun Ying, Scutari Gesualdo, Facchinei Francisco, Sadler Brian M.

This paper studies Dictionary Learning problems wherein the learning task is distributed over a multi-agent network, modeled as a time-varying directed graph. This formulation is relevant, for instance, in Big Data scenarios where massive amounts of data are collected/stored in different locations (e.g., sensors, clouds) and aggregating and/or processing all data in a fusion center might be inefficient or unfeasible, due to resource limitations, communication overheads or privacy issues. We develop a unified decentralized algorithmic framework for this class of nonconvex problems, which is proved to converge to stationary solutions at a sublinear rate. The new method hinges on Successive Convex Approximation techniques, coupled with a decentralized tracking mechanism aiming at locally estimating the gradient of the smooth part of the sum-utility. To the best of our knowledge, this is the first provably convergent decentralized algorithm for Dictionary Learning and, more generally, bi-convex problems over (time-varying) (di)graphs.
Gruppo di ricerca: Continuous Optimization
keywords
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma