10 papers
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…
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…
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…
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…
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…
On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
Julius Kobialka, Emanuel Sommer, Chris Kolb +3
Bayesian neural network (BNN) posteriors are often considered impractical for inference, as symmetries fragment them, non-identifiabilities inflate dimensionality, and weight-space…
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…
Paths and Ambient Spaces in Neural Loss Landscapes
Daniel Dold, Julius Kobialka, Nicolai Palm +3
Understanding the structure of neural network loss surfaces, particularly the emergence of low-loss tunnels, is critical for advancing neural network theory and practice. In this p…
Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks
Emanuel Sommer, Jakob Robnik, Giorgi Nozadze +2
Despite recent advances, sampling-based inference for Bayesian Neural Networks (BNNs) remains a significant challenge in probabilistic deep learning. While sampling-based approache…
Vine Copula based portfolio level conditional risk measure forecasting
Emanuel Sommer, Karoline Bax, Claudia Czado
Accurately estimating risk measures for financial portfolios is critical for both financial institutions and regulators. However, many existing models operate at the aggregate port…