Emanuel Sommer

According to our database, Emanuel Sommer authored at least 9 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

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

Daniel Dold, Emanuel Sommer, Julius Kobialka, Oliver Dürr, David Rügamer

CoRR, May, 2026

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

Emanuel Sommer, David Rügamer

CoRR, May, 2026

bde: A Python Package for Bayesian Deep Ensembles via MILE.

Vyron Arvanitis, Angelos Aslanidis, Emanuel Sommer, David Rügamer

CoRR, May, 2026

Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles.

Emanuel Sommer, Rickmer Schulte, Sarah Deubner, Julius Kobialka, David Rügamer

CoRR, April, 2026

On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors.

Julius Kobialka, Emanuel Sommer, Chris Kolb, Juntae Kwon, Daniel Dold, David Rügamer

CoRR, March, 2026

Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?

Emanuel Sommer, Kangning Diao, Jakob Robnik, Uros Seljak, David Rügamer

CoRR, February, 2026

2025

Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks.

Emanuel Sommer, Jakob Robnik, Giorgi Nozadze, Uros Seljak, David Rügamer

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Paths and Ambient Spaces in Neural Loss Landscapes.

Daniel Dold, Julius Kobialka, Nicolai Palm, Emanuel Sommer, David Rügamer, Oliver Dürr

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?

Emanuel Sommer, Lisa Wimmer, Theodore Papamarkou, Ludwig Bothmann, Bernd Bischl, David Rügamer

Proceedings of the Forty-first International Conference on Machine Learning, 2024