Ground state energy functional with Hartree-Fock efficiency and chemical accuracy

Abstract

We introduce the Deep Post-Hartree-Fock (DeePHF) method, a machine learning based scheme for constructing accurate and transferable models for the ground-state energy of electronic structure problems. DeePHF predicts the energy difference between results of highly accurate models such as the coupled cluster method and low accuracy models such as the the Hartree-Fock (HF) method, using the ground-state electronic orbitals as the input. It preserves all the symmetries of the original high accuracy model. The added computational cost is less than that of the reference HF or DFT and scales linearly with respect to system size. We examine the performance of DeePHF on organic molecular systems using publicly available datasets and obtain the state-of-art performance, particularly on large datasets.

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Gaussian Error Linear Units (GELUs)
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Less is more: sampling chemical space with active learning
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Deep Learning Scaling is Predictable, Empirically
• Deep Potential: a general representation of a many-body potential energy surface
• 86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning

Cited by in corpus (18)

• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Perspective on integrating machine learning into computational chemistry and materials science
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
• Prospects of Quantum Computing for Molecular Sciences
• Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states
• KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search
• Integrating Machine Learning with Physics-Based Modeling
• Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space
• An orbital-based representation for accurate Quantum Machine Learning
• DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
• Mean-Field Density Matrix Decompositions
• Low-data deep quantum chemical learning for accurate MP2 and coupled-cluster correlations
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Machine learning for accuracy in density functional approximations
• Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning
• Molecular Energy Learning Using Alternative Blackbox Matrix-Matrix Multiplication Algorithm for Exact Gaussian Process