# Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning

arXiv: https://arxiv.org/abs/1910.14179 · HTML: https://mlsanity.com/paper/1910.14179/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2019.

## Built on by (most cited first, 4 of 4)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification](https://mlsanity.com/paper/2304.05165/) (2023)
- [Bayesian Autoencoders for Drift Detection in Industrial Environments](https://mlsanity.com/paper/2107.13249/) (2021)
- [Advancing sleep detection by modelling weak label sets: A novel weakly supervised learning approach](https://mlsanity.com/paper/2402.17601/) (2024)

## Abstract (arXiv)

The role of uncertainty quantification (UQ) in deep learning has become crucial with growing use of predictive models in high-risk applications. Though a large class of methods exists for measuring deep uncertainties, in practice, the resulting estimates are found to be poorly calibrated, thus making it challenging to translate them into actionable insights. A common workaround is to utilize a separate recalibration step, which adjusts the estimates to compensate for the miscalibration. Instead, we propose to repurpose the heteroscedastic regression objective as a surrogate for calibration and enable any existing uncertainty estimator to be inherently calibrated. In addition to eliminating the need for recalibration, this also regularizes the training process. Using regression experiments, we demonstrate the effectiveness of the proposed heteroscedastic calibration with two popular uncertainty estimators.