Asynchronous Gossip for Averaging and Spectral Ranking

Borkar, VS and Makhijani, Rahul and Sundaresan, Rajesh (2014) Asynchronous Gossip for Averaging and Spectral Ranking. In: IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 8 (4). pp. 703-716.

PDF ieee_jou_sel_top_sig_pro_8-4_703_2014.pdf - Published Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

We consider two variants of the classical gossip algorithm. The first variant is a version of asynchronous stochastic approximation. We highlight a fundamental difficulty associated with the classical asynchronous gossip scheme, viz., that it may not converge to a desired average, and suggest an alternative scheme based on reinforcement learning that has guaranteed convergence to the desired average. We then discuss a potential application to a wireless network setting with simultaneous link activation constraints. The second variant is a gossip algorithm for distributed computation of the Perron-Frobenius eigenvector of a nonnegative matrix. While the first variant draws upon a reinforcement learning algorithm for an average cost controlled Markov decision problem, the second variant draws upon a reinforcement learning algorithm for risk-sensitive control. We then discuss potential applications of the second variant to ranking schemes, reputation networks, and principal component analysis.

Item Type:	Journal Article
Publication:	IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING
Additional Information:	Copy right for this article belongs to the IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 445 HOES LANE, PISCATAWAY, NJ 08855-4141 USA
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	18 Sep 2014 09:10
Last Modified:	27 Feb 2019 10:19
URI:	http://eprints.iisc.ac.in/id/eprint/49898

Actions (login required)

View Item