collaborators

9 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

On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference

Daniel Dold, Emanuel Sommer, Julius Kobialka +2

While parameter-efficient fine-tuning methods like low-rank adaptation (LoRA) are standard for large language models, principled estimation of epistemic uncertainty remains challen…

cs.LG2026

Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning

Emanuel Sommer, David Rügamer

The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and effic…

cs.LG2026

Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?

Emanuel Sommer, Kangning Diao, Jakob Robnik +2

Scaling inference methods such as Markov chain Monte Carlo to high-dimensional models remains a central challenge in Bayesian deep learning. A promising recent proposal, microcanon…

cs.LG2026

bde: A Python Package for Bayesian Deep Ensembles via MILE

Vyron Arvanitis, Angelos Aslanidis, Emanuel Sommer +1

bde is a user-friendly Python package for Bayesian Deep Ensembles with a particular focus on tabular data. Built on an efficient JAX implementation of the sampling-based inference…

cs.LG2026

Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles

Emanuel Sommer, Rickmer Schulte, Sarah Deubner +2

Bayesian Deep Ensembles (BDEs) represent a powerful approach for uncertainty quantification in deep learning, combining the robustness of Deep Ensembles (DEs) with flexible multi-c…