5 papers
Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors
Richard Bergna, Stefan Depeweg, José Miguel Hernández-Lobato
Prior-Fitted Networks (PFNs) amortize Bayesian prediction by meta-learning over a synthetic task prior, but their standard output is a posterior predictive distribution over noisy…
Activation-Space Uncertainty Quantification for Pretrained Networks
Richard Bergna, Stefan Depeweg, Sergio Calvo-Ordoñez +3
Reliable uncertainty estimates are crucial for deploying pretrained models; yet, many strong methods for quantifying uncertainty require retraining, Monte Carlo sampling, or expens…
Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes
Richard Bergna, Stefan Depeweg, Sergio Calvo Ordonez +3
Uncertainty quantification in neural networks through methods such as Dropout, Bayesian neural networks and Laplace approximations is either prone to underfitting or computationall…
Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy Search
Amna Najib, Stefan Depeweg, Phillip Swazinna
Batch reinforcement learning enables policy learning without direct interaction with the environment during training, relying exclusively on previously collected sets of interactio…
Lightning UQ Box: A Comprehensive Framework for Uncertainty Quantification in Deep Learning
Nils Lehmann, Jakob Gawlikowski, Adam J. Stewart +4
Uncertainty quantification (UQ) is an essential tool for applying deep neural networks (DNNs) to real world tasks, as it attaches a degree of confidence to DNN outputs. However, de…