Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
Optimally-Weighted Herding is Bayesian Quadrature
Ferenc Huszar, David Duvenaud
Abstract:
Herding and kernel herding are deterministic methods of choosing samples which summarise a probability distribution. A related task is choosing samples for estimating integrals using Bayesian quadrature. We show that the criterion minimised when selecting samples in kernel herding is equivalent to the posterior variance in Bayesian quadrature. We then show that sequential Bayesian quadrature can be viewed as a weighted version of kernel herding which achieves performance superior to any other weighted herding method. We demonstrate empirically a rate of convergence faster than O(1/N). Our results also imply an upper bound on the empirical error of the Bayesian quadrature estimate.
Keywords:
Pages: 377-386
PS Link:
PDF Link: /papers/12/p377-huszar.pdf
BibTex:
@INPROCEEDINGS{Huszar12,
AUTHOR = "Ferenc Huszar and David Duvenaud",
TITLE = "Optimally-Weighted Herding is Bayesian Quadrature",
BOOKTITLE = "Proceedings of the Twenty-Eighth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-12)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2012",
PAGES = "377--386"
}


hosted by DSL   •   site info   •   help