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.
Decentralized Dictionary Learning Over Time-Varying Digraphs / Daneshmand, Amir; Sun, Ying; Scutari, Gesualdo; Facchinei, Francisco; Sadler, Brian M.. - In: JOURNAL OF MACHINE LEARNING RESEARCH. - ISSN 1532-4435. - 20(2019), pp. 1-62.
|Titolo:||Decentralized Dictionary Learning Over Time-Varying Digraphs|
FACCHINEI, Francisco (Corresponding author)
|Data di pubblicazione:||2019|
|Citazione:||Decentralized Dictionary Learning Over Time-Varying Digraphs / Daneshmand, Amir; Sun, Ying; Scutari, Gesualdo; Facchinei, Francisco; Sadler, Brian M.. - In: JOURNAL OF MACHINE LEARNING RESEARCH. - ISSN 1532-4435. - 20(2019), pp. 1-62.|
|Appartiene alla tipologia:||01a Articolo in rivista|