Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables

2017-06-26 · Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft

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.

📄 PDF Abstract BibTeX arXiv:1706.08495

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Reinforcement Learning

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

2017-10-19 · ICML 2018 7 · Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft

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 com…

Active Learning Decision Making reinforcement-learning Reinforcement Learning+1

Information-theoretic Analysis of Test Data Sensitivity in Uncertainty

2023-07-23 · Futoshi Futami, Tomoharu Iwata

Bayesian inference is often utilized for uncertainty quantification tasks. A recent analysis by Xu and Raginsky 2022 rigorously decomposed the predictive uncertainty in Bayesian inference into two uncertainties, called a…

Bayesian Inference Meta-Learning Sensitivity Uncertainty Quantification

Variational Uncertainty Decomposition for In-Context Learning

2025-09-02 · I. Shavindra Jayasekera, Jacob Si, Filippo Valdettaro, Wenlong Chen 외 arxiv

As large language models (LLMs) gain popularity in conducting prediction tasks in-context, understanding the sources of uncertainty in in-context learning becomes essential to ensuring reliability. The recent hypothesis …

Bayesian Inference

Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables

2019-11-01 · Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Bayesian Neural Networks with Latent Variables (BNN+LVs) capture predictive uncertainty by explicitly modeling model uncertainty (via priors on network weights) and environmental stochasticity (via a latent input noise v…

Sensitivity Analysis for Predictive Uncertainty in Bayesian Neural Networks

2017-12-10 · Stefan Depeweg, José Miguel Hernández-Lobato, Steffen Udluft, Thomas Runkler

We derive a novel sensitivity analysis of input variables for predictive epistemic and aleatoric uncertainty. We use Bayesian neural networks with latent variables as a model class and illustrate the usefulness of our se…

Sensitivity