Jonas Köhler

Jonas Köhler

Auto-generated profile, based on publicly available information

Jonas Köhler

Microsoft Research AI for Science, Cambridge, UK

Research Focus & Metrics

Academic Career Length

32Years (1995-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 September 2019 in Science
Verified
Journal Article
Closed access
PDF file
FNFrank Noé
Frank Noé
SOSimon Olsson
Simon Olsson
JKJonas Köhler
Jonas Köhler
HWHao Wu
Hao Wu
Efficient sampling of equilibrium states: Molecular dynamics or Monte Carlo methods can be used to sample equilibrium states, but these methods become computationally expensive for complex systems, where the transition from one equilibrium state to another may only occur through rare events. Noé et al. used neural networks and deep learning to generate distributions of independent soft condensed-matter samples at equilibrium (see the Perspective by Tuckerman). Supervised training is used to construct invertible transformations between the coordinates of the complex system of interest and simple Gaussian coordinates of the same dimensionality. Thus, configurations can be sampled in this simpler coordinate system and then transformed back into the complex one using the correct statistical weighting. Science , this issue p. eaaw1147 ; see also p. 982

1 January 2016
Verified
Conference Paper
Closed access
KAKhalid Al-Khatib
Khalid Al-Khatib
HWHenning Wachsmuth
Henning Wachsmuth
MHMatthias Hagen
Matthias Hagen
JKJonas Köhler
Jonas Köhler
BSBenno Stein
Benno Stein

21 January 2025 in The Journal of Chemical Physics
Verified
Journal Article
Closed access
LCLixue Cheng
Lixue Cheng
PSP. Bernát Szabó
P. Bernát Szabó
ZSZeno Schätzle
Zeno Schätzle
DKDerk P. Kooi
Derk P. Kooi
JKJonas Köhler
Jonas Köhler
AFAdam Foster
Adam Foster
Variational ab initio methods in quantum chemistry stand out among other methods in providing direct access to the wave function. This allows, in principle, straightforward extraction of any other observable of interest, besides the energy, but, in practice, this extraction is often technically difficult and computationally impractical. Here, we consider the electron density as a central observable in quantum chemistry and introduce a novel method to obtain accurate densities from real-space many-electron wave functions by representing the density with a neural network that captures known asymptotic properties and is trained from the wave function by score matching and noise-contrastive estimation. We use variational quantum Monte Carlo with deep-learning Ansätze to obtain highly accurate wave functions free of basis set errors and from them, using our novel method, correspondingly accurate electron densities, which we demonstrate by calculating dipole moments, nuclear forces, contact densities, and other density-based properties.

1 January 1995 in Journal of Inverse and Ill-posed Problems
Verified
Journal Article
Closed access
PDF file
JKJ. Köhler
J. Köhler
UTU. Tautenhanh
U. Tautenhanh

23 June 2021 in arXiv
Verified
Preprint
Open access
PDF file
AHAdrian Hoffmann
Adrian Hoffmann
CFClaudio Fanconi
Claudio Fanconi
RRRahul Rade
Rahul Rade
JKJonas Kohler
Jonas Kohler
Deep neural networks that yield human interpretable decisions by architectural design have lately become an increasingly popular alternative to post hoc interpretation of traditional black-box models. Among these networks, the arguably most widespread approach is so-called prototype learning, where similarities to learned latent prototypes serve as the basis of classifying an unseen data point. In this work, we point to an important shortcoming of such approaches. Namely, there is a semantic gap between similarity in latent space and similarity in input space, which can corrupt interpretability. We design two experiments that exemplify this issue on the so-called ProtoPNet. Specifically, we find that this network's interpretability mechanism can be led astray by intentionally crafted or even JPEG compression artefacts, which can produce incomprehensible decisions. We argue that practitioners ought to have this shortcoming in mind when deploying prototype-based models in practice.

21 August 2026 in Nature Communications
Verified
Journal Article
Open access
PDF file
AFAdam Foster
Adam Foster
ZSZeno Schätzle
Zeno Schätzle
PSP. Bernát Szabó
P. Bernát Szabó
LCLixue Cheng
Lixue Cheng
JKJonas Köhler
Jonas Köhler
JHJan Hermann
Jan Hermann
Reliable description of bond breaking remains a major challenge for quantum chemistry due to the multireference character of the electronic structure in dissociating species. Multireference methods in particular suffer from large computational cost, which under the normal paradigm has to be paid anew for each system at a full price, ignoring commonalities in electronic structure across molecules. Quantum Monte Carlo with deep neural networks uniquely offers to exploit such commonalities by pretraining transferable wavefunction models, but all such attempts were so far limited in scope. Here, we bring this paradigm to fruition with Orbformer, a transferable wavefunction model pretrained on 22,000 equilibrium and dissociating structures that can be fine-tuned on unseen molecules reaching an accuracy–cost ratio rivalling classical multireference methods. On established benchmarks as well as more challenging bond dissociations and Diels–Alder reactions, Orbformer is the only method that consistently converges to chemical accuracy (1 kcal/mol). This work turns the idea of amortizing the cost of solving the Schrödinger equation over many molecules into a practical approach in quantum chemistry.