Reliable Neural Networks for Regression Uncertainty Estimation
This addresses uncertainty estimation for regression tasks in deep learning, which is crucial for reliable AI applications, but it appears incremental as it builds on existing frameworks.
The paper tackled the challenge of estimating predictive uncertainty in deep neural networks for regression by proposing a loss function based on the Bayesian Validation Metric framework with ensemble learning. The method showed competitive performance with state-of-the-art methods on in-distribution data and superior robustness on out-of-distribution data.
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.