13 citations · 16 across the 6 of their papers we have counts for
9 papers
Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned
Kajetan Schweighofer, Barbara Brune, Lukas Gruber +11
There is an increasing adoption of artificial intelligence in safety-critical applications, yet practical schemes for certifying that AI systems are safe, lawful and socially accep…
Rethinking Losses for Diffusion Bridge Samplers
Sebastian Sanokowski, Lukas Gruber, Christoph Bartmann +2
Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outper…
Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
Lukas Gruber, Markus Holzleitner, Johannes Lehner +2
Estimating the ratio of two probability densities from finitely many samples, is a central task in machine learning and statistics. In this work, we show that a large class of kern…
Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
Benedikt Alkin, Andreas Fürst, Simon Schmid +3
Neural operators, serving as physics surrogate models, have recently gained increased interest. With ever increasing problem complexity, the natural question arises: what is an eff…
G-Signatures: Global Graph Propagation With Randomized Signatures
Bernhard Schäfl, Lukas Gruber, Johannes Brandstetter +1
Graph neural networks (GNNs) have evolved into one of the most popular deep learning architectures. However, GNNs suffer from over-smoothing node information and, therefore, strugg…
Hopular: Modern Hopfield Networks for Tabular Data
Bernhard Schäfl, Lukas Gruber, Angela Bitto-Nemling +1
While Deep Learning excels in structured data as encountered in vision and natural language processing, it failed to meet its expectations on tabular data. For tabular data, Suppor…
Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER
Markus Holzleitner, Lukas Gruber, José Arjona-Medina +2
We prove under commonly used assumptions the convergence of actor-critic reinforcement learning algorithms, which simultaneously learn a policy function, the actor, and a value fun…
A physical protocol for observers near the boundary to obtain bulk information in quantum gravity
Chandramouli Chowdhury, Olga Papadoulaki, Suvrat Raju
We consider a set of observers who live near the boundary of global AdS, and are allowed to act only with simple low-energy unitaries and make measurements in a small interval of t…
Modern Hopfield Networks and Attention for Immune Repertoire Classification
Michael Widrich, Bernhard Schäfl, Hubert Ramsauer +8
A central mechanism in machine learning is to identify, store, and recognize patterns. How to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more…