Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables
This work addresses uncertainty quantification for researchers and practitioners in machine learning, particularly in active learning and safe reinforcement learning, but it is incremental as it builds on existing Bayesian neural network frameworks.
The paper tackles the problem of decomposing predictive uncertainty into epistemic and aleatoric components in Bayesian neural networks with latent variables, and demonstrates its application in active learning and safe reinforcement learning, showing improved performance in experiments.
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.