Skip to main navigation Skip to search Skip to main content

Trustworthy Prediction with Gaussian Process Knowledge Scores

  • University of Edinburgh
  • Stony Brook University

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

Abstract

Probabilistic models are often used to make predictions in regions of the data space where no observations are available, but it is not always clear whether such predictions are well-informed by previously seen data. In this paper, we propose a knowledge score for predictions from Gaussian process regression (GPR) models that quantifies the extent to which observing data have reduced our uncertainty about a prediction. The knowledge score is interpretable and naturally bounded between 0 and 1. We demonstrate in several experiments that the knowledge score can anticipate when predictions from a GPR model are accurate, and that this anticipation improves performance in tasks such as anomaly detection, extrapolation, and missing data imputation. Source code for this project is available online at https://github.com/KurtButler/GP-knowledge.

Original languageEnglish
Title of host publication2025 33rd European Signal Processing Conference, EUSIPCO 2025 - Proceedings
PublisherEuropean Signal Processing Conference, EUSIPCO
Pages875-879
Number of pages5
ISBN (Electronic)9789464593624
DOIs
StatePublished - 2025
Event33rd European Signal Processing Conference, EUSIPCO 2025 - Palermo, Italy
Duration: Sep 8 2025Sep 12 2025

Publication series

NameEuropean Signal Processing Conference
ISSN (Print)2219-5491

Conference

Conference33rd European Signal Processing Conference, EUSIPCO 2025
Country/TerritoryItaly
CityPalermo
Period09/8/2509/12/25

Keywords

  • anomaly detection
  • Gaussian processes
  • predictive distributions
  • regression models
  • trustworthy machine learning

Fingerprint

Dive into the research topics of 'Trustworthy Prediction with Gaussian Process Knowledge Scores'. Together they form a unique fingerprint.

Cite this