CUED Publications database

Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning

Depeweg, S and Hernandez-Lobato, JM and Doshi-Velez, F and Udluft, S (2018) Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning. 35th International Conference on Machine Learning, ICML 2018, 3. pp. 1920-1934.

Full text not available from this repository.

Abstract

© 2018 35th International Conference on Machine Learning, ICML 2018. All rights reserved. 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 per- ∗ form 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. ' t Using the decomposition we further define a novel risk-sensitive criterion for reinforcement learning to identify policies that balance expected cost, model-bias and noise aversion.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML cs.LG
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 01 Nov 2017 20:05
Last Modified: 17 Sep 2020 02:46
DOI: