Exact Gaussian process regression with distributed computations

Duc Trung Nguyen, Maurizio Filippone, Pietro Michiardi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Scopus citations

Abstract

Gaussian Processes (GPs) are powerful non-parametric Bayesian models for function estimation, but suffer from high complexity in terms of both computation and storage. To address such issues, approximation methods have flourished in the literature, including model approximations and approximate inference. However, these methods often sacrifice accuracy for scalability. In this work, we present the design and evaluation of a distributed method for exact GP inference, that achieves true model parallelism using simple, high-level distributed computing frameworks. Our experiments show that exact inference at scale is not only feasible, but it also brings substantial benefits in terms of low error rates and accurate quantification of uncertainty.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM Symposium on Applied Computing
PublisherAssociation for Computing Machinery
Pages1286-1295
Number of pages10
ISBN (Print)9781450359337
DOIs
StatePublished - 2019
Event34th Annual ACM Symposium on Applied Computing, SAC 2019 - Limassol, Cyprus
Duration: Apr 8 2019Apr 12 2019

Publication series

NameProceedings of the ACM Symposium on Applied Computing
VolumePart F147772

Conference

Conference34th Annual ACM Symposium on Applied Computing, SAC 2019
Country/TerritoryCyprus
CityLimassol
Period04/8/1904/12/19

Keywords

  • Distributed computing
  • Matrix Factorization
  • Regression

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'Exact Gaussian process regression with distributed computations'. Together they form a unique fingerprint.

Cite this