activity
20242026
collaborators

5 papers

stat.ML2026

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…

stat.ML2026

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…

stat.ML2025

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…

cs.LG2024

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…

cs.CV2024

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…