collaborators

13 papers

cs.LG2026

Guiding Posterior Exploration with Optimizer-Derived Geometry

Moritz Schlager, Emanuel Sommer, Thomas Möllenhoff +1

Sampling-based methods offer a principled approach to uncertainty quantification in Bayesian neural networks. Their practical use, however, is often challenged by the computational…

cs.LG2026

SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks

Adrian Robert Minut, Nico Daheim, Marco Miani +3

Structured weight-uncertainty can improve many aspects of deep learning, but it remains costly to estimate and difficult to implement. Here, we show that these issues can be addres…

cs.LG2026

Variational Model Merging for Pareto Front Estimation in Multitask Finetuning

Hugo Monzón Maldonado, Nico Daheim, Thomas Möllenhoff +2

Pareto fronts are useful to find good task-mixing strategies for multitask finetuning, but they are also costly to compute. To reduce costs, recent works have used existing model m…

cs.LG2026

Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning

Tobias Jan Wieczorek, Leon de Andrade, Thomas Möllenhoff +1

Modern deep learning models remain notoriously prone to overconfidence, limiting their reliability in high-stakes applications. Bayesian methods aim to counter this by learning a d…

stat.ML2026

Joint Model and Data Sparsification via the Marginal Likelihood

Alexander Timans, Thomas Möllenhoff, Christian A. Naesseth +2

Sparse recovery in linear systems underpins applications from signal processing to high-dimensional regression. Sparse Bayesian Learning, grounded in the principle of automatic rel…

cs.AI2026

Position: agentic AI orchestration should be Bayes-consistent

Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to co…