Browse by author
Lookup NU author(s): Dr Onur Teymur, Professor Chris Oates
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Copyright © 2021 by the author(s)Several researchers have proposed minimisation of maximum mean discrepancy (MMD) as a method to quantise probability measures, i.e., to approximate a distribution by a representative point set. We consider sequential algorithms that greedily minimise MMD over a discrete candidate set. We propose a novel non-myopic algorithm and, in order to both improve statistical efficiency and reduce computational cost, we investigate a variant that applies this technique to a mini-batch of the candidate set at each iteration. When the candidate points are sampled from the target, the consistency of these new algorithms-and their mini-batch variants-is established. We demonstrate the algorithms on a range of important computational problems, including optimisation of nodes in Bayesian cubature and the thinning of Markov chain output.
Author(s): Teymur O, Gorham J, Riabiz M, Oates CJ
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: International Conference on Artificial Intelligence and Statistics (AISTATS)
Year of Conference: 2021
Pages: 1027-1035
Acceptance date: 02/04/2021
Publisher: ML Research Press
URL: http://proceedings.mlr.press/v130/teymur21a.html
Series Title: Proceedings of Machine Learning Research
