Consensus in the Wasserstein Metric Space of Probability Measures
Abstract
Distributed consensus in the Wasserstein metric space of probability measures is introduced in this work. Convergence of each agents measure to a common measure value is proven under a weak network connectivity condition. The common measure reached a teach agent is one minimizing a weighted sum of its Wasserstein distance to all initial agent measures. This measure is known as the Wasserstein bary centre. Special cases involving Gaussian measures, empirical measures, and time-invariant network topologies are considered, where convergence rates and average-consensus results are given. This algorithm has potential applicability in computer vision, machine learning and distributed estimation, etc.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 2015
- Accession Number
- AD1042531
Entities
People
- Adrain N. Bishop
- Arnaud Doucet
Organizations
- University of Technology Sydney