96 citations · 109 across the 12 of their papers we have counts for
13 papers
E3J: An Efficient and Open-Source Backend for Euclidean Equivariant Operations on GPU and TPU
Olivier Peltre, Armand Picard, Adrien Pichard +6
We present e3j, a fast Euclid-equivariance backend for geometric deep learning applications with JAX bindings for GPU and TPU. Leveraging both optimized CUDA and Pallas kernels and…
Machine Learning Interatomic Potentials: Advancing Open-Source Software for Efficient and Scalable Molecular Simulation
Christoph Brunken, Titouan Cormier, Lucien Walewski +15
Machine learning interatomic potentials (MLIPs) enable atomistic simulations with near ab initio accuracy at significantly reduced computational cost, but their broader adoption is…
Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs
Eszter Varga-Umbrich, Zachary Weller-Davies, Paul Duckworth +3
Active learning for machine-learning interatomic potentials (MLIPs) must address several challenges to be practical: scaling to large candidate pools, leveraging energy-force super…
Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs
Eszter Varga-Umbrich, Shikha Surana, Paul Duckworth +3
Training machine learning interatomic potentials (MLIPs) for reactive chemistry is often bottlenecked by the high cost of quantum chemical labels and the scarcity of transition sta…
Machine Learning Interatomic Potentials: library for efficient training, model development and simulation of molecular systems
Christoph Brunken, Olivier Peltre, Heloise Chomet +11
Machine Learning Interatomic Potentials (MLIP) are a novel in silico approach for molecular property prediction, creating an alternative to disrupt the accuracy/speed trade-off of…
Universally applicable and tunable graph-based coarse-graining for Machine learning force fields
Christoph Brunken, Sebastien Boyer, Mustafa Omar +7
Coarse-grained (CG) force field methods for molecular systems are a crucial tool to simulate large biological macromolecules and are therefore essential for characterisations of bi…
Local Max-Entropy and Free Energy Principles, Belief Diffusions and their Singularities
Olivier Peltre
A comprehensive picture of three Bethe-Kikuchi variational principles including their relationship to belief propagation (BP) algorithms on hypergraphs is given. The structure of B…
Equivariant Message Passing Neural Network for Crystal Material Discovery
Astrid Klipfel, Olivier Peltre, Najwa Harrati +3
Automatic material discovery with desired properties is a fundamental challenge for material sciences. Considerable attention has recently been devoted to generating stable crystal…
Local Max-Entropy and Free Energy Principles Solved by Belief Propagation
Olivier Peltre
A statistical system is classically defined on a set of microstates by a global energy function , yielding Gibbs probability measures (softmins) …
Message-Passing Algorithms and Homology
Olivier Peltre
This PhD thesis lays out algebraic and topological structures relevant for the study of probabilistic graphical models. Marginal estimation algorithms are introduced as diffusion e…
Extra-fine sheaves and interaction decompositions
Daniel Bennequin, Olivier Peltre, Grégoire Sergeant-Perthuis +1
We introduce an original notion of (upper) extra-fine sheaf on a topological space, for which Čech cohomology in strictly positive degree vanishes. We apply this notion when the to…
Geomstats: A Python Package for Riemannian Geometry in Machine Learning
Nina Miolane, Alice Le Brigant, Johan Mathe +16
We introduce Geomstats, an open-source Python toolbox for computations and statistics on nonlinear manifolds, such as hyperbolic spaces, spaces of symmetric positive definite matri…
A Homological Approach to Belief Propagation and Bethe Approximations
Olivier Peltre
We introduce a differential complex of local observables given a decomposition of a global set of random variables into subsets. Its boundary operator allows us to define a transpo…