Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
This addresses uncertainty quantification for decision-making in machine learning, particularly in active learning and reinforcement learning, but appears incremental as it builds on existing Bayesian neural networks with latent variables.
The paper tackled the problem of decomposing uncertainty in Bayesian deep learning into epistemic and aleatoric components, enabling efficient active learning for heteroscedastic and bimodal noise and defining a risk-sensitive criterion for reinforcement learning that balances expected cost, model-bias, and noise aversion.
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. We show how to extract and decompose uncertainty into epistemic and aleatoric 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 learning to identify policies that balance expected cost, model-bias and noise aversion.