152 citations · 465 across the 17 of their papers we have counts for
18 papers
Flow-matching -- efficient coarse-graining of molecular dynamics without forces
Jonas Köhler, Yaoyi Chen, Andreas Krämer +2
Coarse-grained (CG) molecular simulations have become a standard tool to study molecular processes on time- and length-scales inaccessible to all-atom simulations. Parameterizing C…
Smooth Normalizing Flows
Jonas Köhler, Andreas Krämer, Frank Noé
Normalizing flows are a promising tool for modeling probability distributions in physical systems. While state-of-the-art flows accurately approximate distributions and energies, a…
Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces
Ziyad Sheebaelhamd, Konstantinos Zisis, Athina Nisioti +3
Multi-agent control problems constitute an interesting area of application for deep reinforcement learning models with continuous action spaces. Such real-world applications, howev…
Generating stable molecules using imitation and reinforcement learning
Søren Ager Meldgaard, Jonas Köhler, Henrik Lund Mortensen +3
Chemical space is routinely explored by machine learning methods to discover interesting molecules, before time-consuming experimental synthesizing is attempted. However, these met…
Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks
Antonio Orvieto, Jonas Kohler, Dario Pavllo +2
This paper revisits the so-called vanishing gradient phenomenon, which commonly occurs in deep randomly initialized neural networks. Leveraging an in-depth analysis of neural chain…
Learning Generative Models of Textured 3D Meshes from Real-World Images
Dario Pavllo, Jonas Kohler, Thomas Hofmann +1
Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle p…
Two-Level K-FAC Preconditioning for Deep Learning
Nikolaos Tselepidis, Jonas Kohler, Antonio Orvieto
In the context of deep learning, many optimization methods use gradient covariance information in order to accelerate the convergence of Stochastic Gradient Descent. In particular,…
Training Invertible Linear Layers through Rank-One Perturbations
Andreas Krämer, Jonas Köhler, Frank Noé
Many types of neural network layers rely on matrix properties such as invertibility or orthogonality. Retaining such properties during optimization with gradient-based stochastic o…
Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
Jonas Köhler, Leon Klein, Frank Noé
Normalizing flows are exact-likelihood generative neural networks which approximately transform samples from a simple prior distribution to samples of the probability distribution…
Stochastic Normalizing Flows
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. While classical stoch…
DP-MAC: The Differentially Private Method of Auxiliary Coordinates for Deep Learning
Frederik Harder, Jonas Köhler, Max Welling +1
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 tra…
Equivariant Flows: sampling configurations for multi-body systems with symmetric energies
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. Boltzmann…
Spherical CNNs
Taco S. Cohen, Mario Geiger, Jonas Koehler +1
Convolutional Neural Networks (CNNs) have become the method of choice for learning problems involving 2D planar images. However, a number of problems of recent interest have create…
Convolutional Networks for Spherical Signals
Taco Cohen, Mario Geiger, Jonas Köhler +1
The success of convolutional networks in learning problems involving planar signals such as images is due to their ability to exploit the translation symmetry of the data distribut…
Multigap superconductivity at extremely high temperature: a model for the case of pressurized H2S
A. Bussmann-Holder, J. Kohler, A. Simon +2
It is known that in pressurized H2S the complex electronic structure in the energy range of 200 meV near the chemical potential can be separated into two electronic components, the…
Lattice and polarizability mediated spin activity in EuTiO_3
K. Caslin, R. K. Kremer, Z. Guguchia +3
EuTiO_3 is shown to exhibit novel strong spin-charge-lattice coupling deep in the paramagnetic phase. Its existence is evidenced by an, until now, unknown response of the paramagne…
Structural instability of EuTiO3 from X-ray powder diffraction
J. Köhler, R. Dinnebier, A. Bussmann-Holder
We have recently predicted and subsequently verified experimentally by specific heat measurements that EuTiO3 undergoes a structural phase transition at elevated temperature TS = 2…
Electronic Structure and Lattice dynamics of NaFeAs
Shuiquan Deng, Jürgen Köhler, Arndt Simon
The similarity of the electronic structures of NaFeAs and other Fe pnictides has been demonstrated on the basis of first-principle calculations. The global double-degeneracy of ele…