1 code implementation • 8 May 2024 • Vanni Doffini, O. Anatole von Lilienfeld, Michael A. Nash
We investigate trends in the data-error scaling behavior of machine learning (ML) models trained on discrete combinatorial spaces that are prone-to-mutation, such as proteins or organic small molecules.
1 code implementation • 5 Dec 2022 • Jan Weinreich, Guido Falk von Rudorff, O. Anatole von Lilienfeld
However, we find that encrypted predictions using kernel ridge regression models are a million times more expensive than without encryption.
no code implementations • 4 Feb 2021 • Dominik Lemm, Guido Falk von Rudorff, O. Anatole von Lilienfeld
The computational prediction of atomistic structure is a long-standing problem in physics, chemistry, materials, and biology.
Chemical Physics
no code implementations • 17 Dec 2020 • Jan Weinreich, Nicholas J. Browning, O. Anatole von Lilienfeld
To generate the input representation for a new query compound, FML requires approximate and short molecular dynamics runs.
Chemical Physics
no code implementations • 14 Dec 2020 • Bing Huang, O. Anatole von Lilienfeld
Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal.
Chemical Physics
no code implementations • 6 Aug 2020 • Guido Falk von Rudorff, O. Anatole von Lilienfeld
Massive brute-force compute campaigns relying on demanding ab initio calculations routinely search for novel materials in chemical compound space, the vast virtual set of all conceivable stable combinations of elements and structural configurations which form matter.
Chemical Physics
no code implementations • 30 Jul 2020 • Giorgio Domenichini, Guido Falk von Rudorff, O. Anatole von Lilienfeld
Alchemical perturbation density functional theory has been shown to be an efficient and computationally inexpensive way to explore chemical compound space.
Chemical Physics
no code implementations • 18 Dec 2019 • Julia Westermayr, Felix A. Faber, Anders S. Christensen, O. Anatole von Lilienfeld, Philipp Marquetand
As an ultimate test for our machine learning models, we carry out excited-state dynamics simulations based on the predicted energies, forces and couplings and, thus, show the scopes and possibilities of machine learning for the treatment of electronically excited states.
1 code implementation • 29 Nov 2019 • Guido Falk von Rudorff, O. Anatole von Lilienfeld
We assess the applicability of Alchemical Perturbation Density Functional Theory (APDFT) for quickly and accurately estimating deprotonation energies.
Chemical Physics
no code implementations • 15 Jul 2019 • Guido Falk von Rudorff, O. Anatole von Lilienfeld
Based on thermodynamic integration we introduce atoms in molecules (AIM) using the orbital-free framework of alchemical perturbation density functional theory (APDFT).
Chemical Physics
no code implementations • 5 Sep 2018 • Guido Falk von Rudorff, O. Anatole von Lilienfeld
We introduce an orbital free electron density functional approximation based on alchemical perturbation theory.
Chemical Physics
1 code implementation • 8 Aug 2018 • Peter Zaspel, Bing Huang, Helmut Harbrecht, O. Anatole von Lilienfeld
Inspired by Pople diagrams popular in quantum chemistry, we introduce a hierarchical scheme, based on the multi-level combination (C) technique, to combine various levels of approximations made when calculating molecular energies within quantum chemistry.
Chemical Physics
no code implementations • 16 Oct 2017 • Tristan Bereau, Robert A. DiStasio Jr., Alexandre Tkatchenko, O. Anatole von Lilienfeld
Unlike other potentials, this model is transferable in its ability to handle new molecules and conformations without explicit prior parametrization: All local atomic properties are predicted from ML, leaving only eight global parameters---optimized once and for all across compounds.
Chemical Physics
1 code implementation • 13 Jul 2017 • Bing Huang, O. Anatole von Lilienfeld
In analogy to the DNA sequence in a gene encoding its function, constituting amons encode a query molecule's properties.
Chemical Physics
no code implementations • J. Chem. Theory Comput. 2017 • Felix A. Faber, Luke Hutchison, Bing Huang, Justin Gilmer, Samuel S. Schoenholz, George E. Dahl, Oriol Vinyals, Steven Kearnes, Patrick F. Riley, O. Anatole von Lilienfeld
We investigate the impact of choosing regressors and molecular representations for the construction of fast machine learning (ML) models of thirteen electronic ground-state properties of organic molecules.
Ranked #18 on Formation Energy on QM9
1 code implementation • 23 Jan 2017 • Christopher R. Collins, Geoffrey J. Gordon, O. Anatole von Lilienfeld, David J. Yaron
A set of molecular descriptors whose length is independent of molecular size is developed for machine learning models that target thermodynamic and electronic properties of molecules.
1 code implementation • 22 Aug 2016 • Bing Huang, O. Anatole von Lilienfeld
The predictive accuracy of Machine Learning (ML) models of molecular properties depends on the choice of the molecular representation.
Chemical Physics
1 code implementation • 26 Oct 2015 • Raghunathan Ramakrishnan, O. Anatole von Lilienfeld
We review recent studies dealing with the generation of machine learning models of molecular and solid properties.
Chemical Physics
no code implementations • 29 Jun 2015 • Louis-François Arsenault, O. Anatole von Lilienfeld, Andrew J. Millis
Machine learning methods for solving the equations of dynamical mean-field theory are developed.
no code implementations • 8 Apr 2015 • Raghunathan Ramakrishnan, Mia Hartmann, Enrico Tapavicza, O. Anatole von Lilienfeld
For a training set of 10 thousand molecules, CC2 excitation energies can be reproduced to within $\pm$0. 1 eV for the remaining molecules.
Chemical Physics
1 code implementation • 25 Mar 2015 • Felix Faber, Alexander Lindmaa, O. Anatole von Lilienfeld, Rickard Armiento
We introduce and evaluate a set of feature vector representations of crystal structures for machine learning (ML) models of formation energies of solids.
Chemical Physics
no code implementations • 5 Aug 2014 • Louis-François Arsenault, Alejandro Lopez-Bezanilla, O. Anatole von Lilienfeld, Andrew J. Millis
Machine learning methods are applied to finding the Green's function of the Anderson impurity model, a basic model system of quantum many-body condensed-matter physics.