Summary: The Gaussian Process Density Sampler
Ryan Prescott Adams #
Cavendish Laboratory
University of Cambridge
Cambridge CB3 0HE, UK
rpa23@cam.ac.uk
Iain Murray
Dept. of Computer Science
University of Toronto
Toronto, Ontario. M5S 3G4
murray@cs.toronto.edu
David J.C. MacKay
Cavendish Laboratory
University of Cambridge
Cambridge CB3 0HE, UK
mackay@mrao.cam.ac.uk
Abstract
We present the Gaussian Process Density Sampler (GPDS), an exchangeable gen­
erative model for use in nonparametric Bayesian density estimation. Samples
drawn from the GPDS are consistent with exact, independent samples from a fixed

Source: Adams, Ryan Prescott - Department of Electrical and Computer Engineering, University of Toronto

Collections: Computer Technologies and Information Sciences