MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
arXiv:2411.17011 · doi:10.1063/5.0250837
Abstract
In this work, we present MOLPIPx, a versatile library designed to seamlessly integrate Permutationally Invariant Polynomials (PIPs) with modern machine learning frameworks, enabling the efficient development of linear models, neural networks, and Gaussian process models. These methodologies are widely employed for parameterizing potential energy surfaces across diverse molecular systems. MOLPIPx leverages two powerful automatic differentiation engines -JAX and EnzymeAD-Rust- to facilitate the efficient computation of energy gradients and higher-order derivatives, which are essential for tasks such as force field development and dynamic simulations. MOLPIPx is available at https://github.com/ChemAI-Lab/molpipx.
13 pages, 7 figures, and 6 listings
References in corpus (40)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Machine Learning of Accurate Energy-Conserving Molecular Force Fields
- Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
- GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
- On the accuracy of the MB-pol many-body potential for water: Interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice
- sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
- Bayesian optimization for tuning and selecting hybrid-density functionals
- Perspective on integrating machine learning into computational chemistry and materials science
- -Machine Learning for Potential Energy Surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) Level of Theory
- Gaussian Process Regression for Geometry Optimization
- Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
- Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes
- Learning the exchange-correlation functional from nature with fully differentiable density functional theory
- Automatic differentiation in quantum chemistry with an application to fully variational Hartree-Fock
- Towards empirical force fields that match experimental observables
- Universal Machine Learning for the Response of Atomistic Systems to External Fields
- Bayesian optimization for the inverse scattering problem in quantum reaction dynamics
- High-Dimensional Potential Energy Surfaces for Molecular Simulations
- Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
- Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
- Atomic Permutationally Invariant Polynomials for Fitting Molecular Force Fields
- Differentiable quantum chemistry with PySCF for molecules and materials at the mean-field level and beyond
- Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
- Learning Invariances using the Marginal Likelihood
- GAUCHE: A Library for Gaussian Processes in Chemistry
- Perspective: Non-conventional Force Fields for Applications in Spectroscopy and Chemical Reaction Dynamics
- Gaussian Process Model for Extrapolation of Scattering Observables for Complex Molecules: from Benzene to Benzonitrile
- Grad DFT: a software library for machine learning enhanced density functional theory
- Automatic Differentiation for Orbital-Free Density Functional Theory
- Quantum calculations on a new CCSD(T) machine-learned PES reveal the leaky nature of gas-phase and ethanol conformers
- Inverse molecular design and parameter optimization with Hückel theory using automatic differentiation
- Quantum Gaussian process model of potential energy surface for a polyatomic molecule
- Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules
- Performant Automatic Differentiation of Local Coupled Cluster Theories: Response Properties and Ab Initio Molecular Dynamics
- Differentiable quantum computational chemistry with PennyLane
- Molecular dynamics-driven global tetra-atomic potential energy surfaces: Application to the AlF dimer
- Permutation Invariant Representations with Applications to Graph Deep Learning
- Gaussian Processes with Spectral Delta kernel for higher accurate Potential Energy surfaces for large molecules
- Lineax: unified linear solves and linear least-squares in JAX and Equinox
- Leveraging Normalizing Flows for Orbital-Free Density Functional Theory