Back to Search
Start Over
Decentralized Dictionary Learning Over Time-Varying Digraphs.
- Source :
-
Journal of Machine Learning Research . 2019, Vol. 20 Issue 137-159, p1-62. 62p. - Publication Year :
- 2019
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
- Subjects :
- *DIRECTED graphs
*STORE location
*MULTISENSOR data fusion
*LEARNING problems
Subjects
Details
- Language :
- English
- ISSN :
- 15324435
- Volume :
- 20
- Issue :
- 137-159
- Database :
- Academic Search Index
- Journal :
- Journal of Machine Learning Research
- Publication Type :
- Academic Journal
- Accession number :
- 139384373