collaborators

9 papers

cs.LG2026

A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies

Frieder Wizgall, Georg Tirpitz, Moritz Seiler +2

Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential. This often requires disentangl…

cs.LG2026

Muon is Not That Special: Random or Inverted Spectra Work Just as Well

Zakhar Shumaylov, Nathaël Da Costa, Peter Zaika +6

The recent empirical success of the Muon optimizer has renewed interest in non-Euclidean optimization, typically justified by similarities with second-order methods, and linear min…

cs.LG2026

Rethinking Approximate Gaussian Inference in Classification

Bálint Mucsányi, Nathaël Da Costa, Philipp Hennig

In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capt…

cs.LG2025

sbi reloaded: a toolkit for simulation-based inference workflows

Jan Boelts, Michael Deistler, Manuel Gloeckler +30

Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a…

cs.LG2025

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning

Patrik Reizinger, Bálint Mucsányi, Siyuan Guo +3

Self-supervised feature learning and pretraining methods in reinforcement learning (RL) often rely on information-theoretic principles, termed mutual information skill learning (MI…

cs.LG2025

Logit Reweighting for Topic-Focused Summarization

Joschka Braun, Bálint Mucsányi, Seyed Ali Bahrainian

Generating abstractive summaries that adhere to a specific topic remains a significant challenge for language models. While standard approaches, such as fine-tuning, are resource-i…