Reliable Neural Networks for Regression Uncertainty Estimation
arXiv:2109.08213 · doi:10.1016/j.ress.2022.108811
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.
References in corpus (11)
- Efficient Estimation of Word Representations in Vector Space
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
- Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
- Evidential Deep Learning to Quantify Classification Uncertainty
- Bayesian Deep Ensembles via the Neural Tangent Kernel
- Evaluating and Calibrating Uncertainty Prediction in Regression Tasks
- A Generalized Bayesian Approach to Model Calibration
- Expectation Propagation for Neural Networks with Sparsity-promoting Priors
- A General Model Validation and Testing Tool
- Maximum Likelihood Uncertainty Estimation: Robustness to Outliers