English

High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach

Machine Learning 2019-04-10 v3

Abstract

This paper considers the generation of prediction intervals (PIs) by neural networks for quantifying uncertainty in regression tasks. It is axiomatic that high-quality PIs should be as narrow as possible, whilst capturing a specified portion of data. We derive a loss function directly from this axiom that requires no distributional assumption. We show how its form derives from a likelihood principle, that it can be used with gradient descent, and that model uncertainty is accounted for in ensembled form. Benchmark experiments show the method outperforms current state-of-the-art uncertainty quantification methods, reducing average PI width by over 10%.

Keywords

Cite

@article{arxiv.1802.07167,
  title  = {High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach},
  author = {Tim Pearce and Mohamed Zaki and Alexandra Brintrup and Andy Neely},
  journal= {arXiv preprint arXiv:1802.07167},
  year   = {2019}
}
R2 v1 2026-06-23T00:27:48.217Z