Abstract

Recent machine learning advances have proposed black-box estimation of unknown continuous-time system dynamics directly from data. However, earlier works are based on approximative solutions or point estimates. We propose a novel Bayesian nonparametric model that uses Gaussian processes to infer posteriors of unknown ODE systems directly from data. We derive sparse variational inference with decoupled functional sampling to represent vector field posteriors. We also introduce a probabilistic shooting augmentation to enable efficient inference from arbitrarily long trajectories.The method demonstrates the benefit of computing vector field posteriors, with predictive uncertainty scores outperforming alternative methods on multiple ODE learning tasks.
Original languageEnglish
Title of host publicationProceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022), PMLR
PublisherJMLR
Pages790-799
Publication statusPublished - 2022
MoE publication typeA4 Conference publication
EventConference on Uncertainty in Artificial Intelligence - Eindhoven, Netherlands
Duration: 1 Aug 20225 Aug 2022
Conference number: 38
https://www.auai.org/uai2022/

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume180
ISSN (Print)2640-3498

Conference

ConferenceConference on Uncertainty in Artificial Intelligence
Abbreviated titleUAI
Country/TerritoryNetherlands
CityEindhoven
Period01/08/202205/08/2022
Internet address

Fingerprint

Dive into the research topics of 'Variational multiple shooting for Bayesian ODEs with Gaussian processes'. Together they form a unique fingerprint.

Cite this