Deep learning with differential Gaussian process flows

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

  • Authors:
  • Pashupati Hegde
  • Markus Heinonen
  • Harri Lahdesmaki
  • Samuel Kaski

Abstract

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate excellent results as compared to deep Gaussian processes and Bayesian neural networks.

Bibliographical metadata

Original languageEnglish
Title of host publicationProceedings of Machine Learning Research: Artificial Intelligence and Statistics 2019
Pages1812-1821
Volume89
Publication statusPublished - 16 Apr 2019
Event22nd International Conference on
Artificial Intelligence and Statistics
- Naha, Japan
Event duration: 16 Apr 201918 Apr 2019

Publication series

NameProceedings of Machine Learning Research
PublisherMLResearchPress
ISSN (Electronic)2640-3498

Conference

Conference22nd International Conference on
Artificial Intelligence and Statistics
Abbreviated titleAISTATS 2019
CountryJapan
CityNaha
Period16/04/1918/04/19

Related information

Researchers

View all