1 citations · 1 across the 5 of their papers we have counts for
8 papers · 1 filter
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…
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…
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…
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…
Kronecker-factored Approximate Curvature (KFAC) From Scratch
Felix Dangel, Bálint Mucsányi, Tobias Weber +1
Kronecker-factored approximate curvature (KFAC) is arguably one of the most prominent curvature approximations in deep learning. Its applications range from optimization to Bayesia…
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…