no code implementations • ICML 2020 • Jonas Köhler, Leon Klein, Frank Noe
We provide a theoretical sufficient criterium showing that the distribution generated by \textit{equivariant} normalizing flows is invariant with respect to these symmetries by design.
1 code implementation • 26 Jan 2023 • Jonas Köhler, Michele Invernizzi, Pim de Haan, Frank Noé
Normalizing flows (NF) are a class of powerful generative models that have gained popularity in recent years due to their ability to model complex distributions with high flexibility and expressiveness.
1 code implementation • 21 Mar 2022 • Jonas Köhler, Yaoyi Chen, Andreas Krämer, Cecilia Clementi, Frank Noé
Coarse-grained (CG) molecular simulations have become a standard tool to study molecular processes on time- and length-scales inaccessible to all-atom simulations.
no code implementations • NeurIPS 2021 • Jonas Köhler, Andreas Krämer, Frank Noé
In this work, we introduce a class of smooth mixture transformations working on both compact intervals and hypertori.
no code implementations • 11 Jul 2021 • Søren Ager Meldgaard, Jonas Köhler, Henrik Lund Mortensen, Mads-Peter V. Christiansen, Frank Noé, Bjørk Hammer
Chemical space is routinely explored by machine learning methods to discover interesting molecules, before time-consuming experimental synthesizing is attempted.
no code implementations • 14 Oct 2020 • Andreas Krämer, Jonas Köhler, Frank Noé
Many types of neural network layers rely on matrix properties such as invertibility or orthogonality.
no code implementations • 3 Jun 2020 • Jonas Köhler, Leon Klein, Frank Noé
We provide a theoretical sufficient criterion showing that the distribution generated by \textit{equivariant} normalizing flows is invariant with respect to these symmetries by design.
1 code implementation • NeurIPS 2020 • Hao Wu, Jonas Köhler, Frank Noé
The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics.
1 code implementation • 15 Oct 2019 • Frederik Harder, Jonas Köhler, Max Welling, Mijung Park
Developing a differentially private deep learning algorithm is challenging, due to the difficulty in analyzing the sensitivity of objective functions that are typically used to train deep neural networks.
no code implementations • 2 Oct 2019 • Jonas Köhler, Leon Klein, Frank Noé
Flows are exact-likelihood generative neural networks that transform samples from a simple prior distribution to the samples of the probability distribution of interest.
2 code implementations • 4 Dec 2018 • Frank Noé, Simon Olsson, Jonas Köhler, Hao Wu
Computing equilibrium states in condensed-matter many-body systems, such as solvated proteins, is a long-standing challenge.
2 code implementations • 14 Sep 2017 • Taco Cohen, Mario Geiger, Jonas Köhler, Max Welling
Many areas of science and egineering deal with signals with other symmetries, such as rotation invariant data on the sphere.