A Novel Regression Loss for Non-Parametric Uncertainty Optimization
arXiv:2101.02726
Abstract
Quantification of uncertainty is one of the most promising approaches to establish safe machine learning. Despite its importance, it is far from being generally solved, especially for neural networks. One of the most commonly used approaches so far is Monte Carlo dropout, which is computationally cheap and easy to apply in practice. However, it can underestimate the uncertainty. We propose a new objective, referred to as second-moment loss (SML), to address this issue. While the full network is encouraged to model the mean, the dropout networks are explicitly used to optimize the model variance. We intensively study the performance of the new objective on various UCI regression datasets. Comparing to the state-of-the-art of deep ensembles, SML leads to comparable prediction accuracies and uncertainty estimates while only requiring a single model. Under distribution shift, we observe moderate improvements. As a side result, we introduce an intuitive Wasserstein distance-based uncertainty measure that is non-saturating and thus allows to resolve quality differences between any two uncertainty estimates.
Accepted at the 3rd Symposium on Advances in Approximate Bayesian Inference (AABI), code is available on: https://github.com/fraunhofer-iais/second-moment-loss. arXiv admin note: substantial text overlap with arXiv:2012.12687
References in corpus (5)
- Weight Uncertainty in Neural Networks
- Improving Output Uncertainty Estimation and Generalization in Deep Learning via Neural Network Gaussian Processes
- 'In-Between' Uncertainty in Bayesian Neural Networks
- Characteristics of Monte Carlo Dropout in Wide Neural Networks
- Approaching Neural Network Uncertainty Realism