Scalable Gaussian process inference with finite-data mean and variance guarantees
Name
1806.10234.pdf
Description
Accepted version
Size
4.55 MB
Format
Adobe PDF
Checksum (MD5)
5d1ae34b4000c452961527b20030e53c
Author(s)
Huggins, Jonathan H.
Broderick, Tamara A
Campbell, Trevor David
Date Issued
April 2019
Journal
Proceedings of the 22ndInternational Conference on Ar-tificial Intelligence and Statistics (AISTATS)
Publisher
PMLR
Citation
Huggins, Jonathan H. et al. “Scalable Gaussian process inference with finite-data mean and variance guarantees.” Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 89 (April 2019): 76-86 © 2019 The Author(s)
Version
Author's final manuscript
Abstract
Gaussian processes (GPs) offer a flexible class of priors for nonparametric Bayesian regression, but popular GP posterior inference methods are typically prohibitively slow or lack desirable finite-data guarantees on quality. We develop a scalable approach to approximate GP regression, with finite-data guarantees on the accuracy of our pointwise posterior mean and variance estimates. Our main contribution is a novel objective for approximate inference in the nonparametric setting: the preconditioned Fisher (pF) divergence. We show that unlike the Kullback-Leibler divergence (used in variational inference), the pF divergence bounds the 2-Wasserstein distance, which in turn provides tight bounds on the pointwise error of mean and variance estimates. We demonstrate that, for sparse GP likelihood approximations, we can minimize the pF divergence efficiently. Our experiments show that optimizing the pF divergence has the same computational requirements as variational sparse GPs while providing comparable empirical performance-in addition to our novel finite-data quality guarantees.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://proceedings.mlr.press/v89/huggins19a.html
