Improving Regression Uncertainty Estimation Under Statistical Change

09/16/2021
by   Tony Tohme, et al.
0

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. A series of experiments on in-distribution data show that the proposed method is competitive with existing state-of-the-art methods. In addition, experiments on out-of-distribution data show that the proposed method is robust to statistical change and exhibits superior predictive capability.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset