A Riemannian gossip approach to subspace learning on Grassmann manifold

Bamdev Mishra, Hiroyuki Kasai, Pratik Jawanpuria, Atul Saroop

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we focus on subspace learning problems on the Grass-mann manifold. Interesting applications in this setting include low-rank matrix completion and low-dimensional multivariate regression, among others. Moti-vated by privacy concerns, we aim to solve such problems in a decentralized setting where multiple agents have access to (and solve) only a part of the whole optimization problem. The agents communicate with each other to ar-rive at a consensus, i.e., agree on a common quantity, via the gossip protocol. We propose a novel cost function for subspace learning on the Grassmann manifold, which is a weighted sum of several sub-problems (each solved by an agent) and the communication cost among the agents. The cost function has a finite sum structure. In the proposed modeling approach, different agents learn individual local subspace but they achieve asymptotic consensus on the global learned subspace. The approach is scalable and parallelizable. Numerical experiments show the ecacy of the proposed decentralized algorithms on various matrix completion and multivariate regression benchmarks.

Original languageEnglish
JournalUnknown Journal
Publication statusPublished - 2017 May 1
Externally publishedYes

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'A Riemannian gossip approach to subspace learning on Grassmann manifold'. Together they form a unique fingerprint.

Cite this