6 papers · 1 filter
Neural surrogates for designing gravitational wave detectors
Carlos Ruiz-Gonzalez, Sören Arlt, Sebastian Lehner +5
Physics simulators are essential in science and engineering, enabling the analysis, control, and design of complex systems. In experimental sciences, they are increasingly used to…
xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity
Maximilian Beck, Kajetan Schweighofer, Sebastian Böck +2
Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While T…
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…
Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
Sebastian Sanokowski, Wilhelm Berghammer, Martin Ennemoser +3
Learning to sample from complex unnormalized distributions over discrete domains emerged as a promising research direction with applications in statistical physics, variational inf…
A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
Sebastian Sanokowski, Sepp Hochreiter, Sebastian Lehner
Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combin…
Variational Annealing on Graphs for Combinatorial Optimization
Sebastian Sanokowski, Wilhelm Berghammer, Sepp Hochreiter +1
Several recent unsupervised learning methods use probabilistic approaches to solve combinatorial optimization (CO) problems based on the assumption of statistically independent sol…