Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables

by   Stefan Depeweg, et al.

Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data. We describe and study in these models a decomposition of predictive uncertainty into its epistemic and aleatoric components. First, we show how such a decomposition arises naturally in a Bayesian active learning scenario by following an information theoretic approach. Second, we use a similar decomposition to develop a novel risk sensitive objective for safe reinforcement learning (RL). This objective minimizes the effect of model bias in environments whose stochastic dynamics are described by BNNs with latent variables. Our experiments illustrate the usefulness of the resulting decomposition in active learning and safe RL settings.


page 1

page 2

page 3

page 4


Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems

Bayesian neural networks (BNNs) with latent variables are probabilistic ...

Sensitivity Analysis for Predictive Uncertainty in Bayesian Neural Networks

We derive a novel sensitivity analysis of input variables for predictive...

Information-theoretic Analysis of Test Data Sensitivity in Uncertainty

Bayesian inference is often utilized for uncertainty quantification task...

Accelerating Stochastic Simulation with Interactive Neural Processes

Stochastic simulations such as large-scale, spatiotemporal, age-structur...

Weighted Tensor Decomposition for Learning Latent Variables with Partial Data

Tensor decomposition methods are popular tools for learning latent varia...

Tackling covariate shift with node-based Bayesian neural networks

Bayesian neural networks (BNNs) promise improved generalization under co...

Supervised Negative Binomial Classifier for Probabilistic Record Linkage

Motivated by the need of the linking records across various databases, w...

Please sign up or login with your details

Forgot password? Click here to reset