English

Reliable Neural Networks for Regression Uncertainty Estimation

Machine Learning 2022-10-14 v2 Machine Learning

Abstract

While deep neural networks are highly performant and successful in a wide range of real-world problems, estimating their predictive uncertainty remains a challenging task. To address this challenge, we propose and implement a loss function for regression uncertainty estimation based on the Bayesian Validation Metric (BVM) framework while using ensemble learning. The proposed loss reproduces maximum likelihood estimation in the limiting case. A series of experiments on in-distribution data show that the proposed method is competitive with existing state-of-the-art methods. Experiments on out-of-distribution data show that the proposed method is robust to statistical change and exhibits superior predictive capability.

Keywords

Cite

@article{arxiv.2109.08213,
  title  = {Reliable Neural Networks for Regression Uncertainty Estimation},
  author = {Tony Tohme and Kevin Vanslette and Kamal Youcef-Toumi},
  journal= {arXiv preprint arXiv:2109.08213},
  year   = {2022}
}
R2 v1 2026-06-24T06:03:11.997Z