5 papers
Show Me What You Don't Know: Efficient Sampling from Invariant Sets for Model Validation
Armand Rousselot, Joran Wendebourg, Ullrich Köthe
The performance of machine learning models is determined by the quality of their learned features. They should be invariant under irrelevant data variation but sensitive to task-re…
From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows
Daniel Galperin, Ullrich Köthe
Learning unsupervised representations that are both semantically meaningful and stable across runs remains a central challenge in modern representation learning. We introduce entro…
Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions
Sander Hummerich, Tristan Bereau, Ullrich Köthe
By reducing resolution, coarse-grained models greatly accelerate molecular simulations, unlocking access to long-timescale phenomena, though at the expense of microscopic informati…
Beyond Diagonal Covariance: Flexible Posterior VAEs via Free-Form Injective Flows
Peter Sorrenson, Lukas Lührs, Hans Olischläger +1
Variational Autoencoders (VAEs) are powerful generative models widely used for learning interpretable latent spaces, quantifying uncertainty, and compressing data for downstream ge…
TRADE: Transfer of Distributions between External Conditions with Normalizing Flows
Stefan Wahl, Armand Rousselot, Felix Draxler +2
Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature…