Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
Stefan Depeweg, Jose-Miguel Hernandez-Lobato, Finale Doshi-Velez, Steffen Udluft
Abstract
Bayesian neural networks with latent variables are scalable and flexible probabilistic models: they account for uncertainty in the estimation of the network weights and, by making use of latent variables, can capture complex noise patterns in the data. Using these models we show how to perform and utilize a decomposition of uncertainty in aleatoric and epistemic components for decision making purposes. This allows us to successfully identify informative points for active learning of functions with heteroscedastic and bimodal noise. Using the decomposition we further define a novel risk-sensitive criterion for reinforcement learningto identify policies that balance expected cost, model-bias and noise aversion.
BibTeX
@InProceedings{pmlr-v80-depeweg18a,
title = {Decomposition of Uncertainty in {B}ayesian Deep Learning for Efficient and Risk-sensitive Learning},
author = {Depeweg, Stefan and Hernandez-Lobato, Jose-Miguel and Doshi-Velez, Finale and Udluft, Steffen},
booktitle = {Proceedings of the 35th International Conference on Machine Learning},
pages = {1184--1193},
year = {2018},
editor = {Dy, Jennifer and Krause, Andreas},
volume = {80},
series = {Proceedings of Machine Learning Research},
month = {10--15 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v80/depeweg18a/depeweg18a.pdf},
url = {https://proceedings.mlr.press/v80/depeweg18a.html},
abstract = {Bayesian neural networks with latent variables are scalable and flexible probabilistic models: they account for uncertainty in the estimation of the network weights and, by making use of latent variables, can capture complex noise patterns in the data. Using these models we show how to perform and utilize a decomposition of uncertainty in aleatoric and epistemic components for decision making purposes. This allows us to successfully identify informative points for active learning of functions with heteroscedastic and bimodal noise. Using the decomposition we further define a novel risk-sensitive criterion for reinforcement learningto identify policies that balance expected cost, model-bias and noise aversion.}
}