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

arXiv: https://arxiv.org/abs/1710.07283 · HTML: https://mlsanity.com/paper/1710.07283/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2017.

## Built on by (most cited first, 5 of 5)

- [Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?](https://mlsanity.com/paper/2209.03302/) (2022)
- [TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning](https://mlsanity.com/paper/2505.11737/) (2025)
- [Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning](https://mlsanity.com/paper/2202.03770/) (2022)
- [Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems](https://mlsanity.com/paper/2112.01675/) (2021)
- [Fill-and-Spill: Deep Reinforcement Learning Policy Gradient Methods for Reservoir Operation Decision and Control](https://mlsanity.com/paper/2403.04195/) (2024)

## Abstract (arXiv)

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.