Ground State Energy Functional with Hartree-Fock Efficiency and Chemical Accuracy.

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.

[1]  M. Plesset,et al.  Note on an Approximation Treatment for Many-Electron Systems , 1934 .

[2]  D. Hartree,et al.  Self-consistent field, with exchange, for beryllium , 1935 .

[3]  P. Hohenberg,et al.  Inhomogeneous Electron Gas , 1964 .

[4]  W. Kohn,et al.  Self-Consistent Equations Including Exchange and Correlation Effects , 1965 .

[5]  J. Cizek.  On the Correlation Problem in Atomic and Molecular Systems. Calculation of Wavefunction Components in Ursell-Type Expansion Using Quantum-Field Theoretical Methods , 1966 .

[6]  T. Gilbert.  Hohenberg--Kohn theorem for nonlocal external potentials , 1975 .

[7]  H. Monkhorst,et al.  Coupled-cluster method for multideterminantal reference states , 1981 .

[8]  Martin Head-Gordon,et al.  Quadratic configuration interaction. A general technique for determining electron correlation energies , 1987 .

[9]  Angela K. Wilson,et al.  Gaussian basis sets for use in correlated molecular calculations. IX. The atoms gallium through krypton , 1993 .

[10]  David,et al.  Gaussian basis sets for use in correlated molecular calculations . Ill . The atoms aluminum through argon , 1999 .

[11]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[12]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[13]  Donald G. Truhlar,et al.  Generalized Gradient Approximation That Recovers the Second-Order Density-Gradient Expansion with Optimized Across-the-Board Performance , 2011 .

[14]  D. Truhlar,et al.  Validation of electronic structure methods for isomerization reactions of large organic molecules. , 2011, Physical chemistry chemical physics : PCCP.

[15]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[16]  Michele Benzi,et al.  Decay Properties of Spectral Projectors with Applications to Electronic Structure , 2012, SIAM Rev..

[17]  Lexing Ying,et al.  Compressed Representation of Kohn-Sham Orbitals via Selected Columns of the Density Matrix. , 2014, Journal of chemical theory and computation.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Kevin Gimpel,et al.  Gaussian Error Linear Units (GELUs) , 2016 .

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Klaus-Robert Müller,et al.  Machine learning of accurate energy-conserving molecular force fields , 2016, Science Advances.

[22]  E. Weinan,et al.  Deep Potential: a general representation of a many-body potential energy surface , 2017, 1707.01478.

[23]  Klaus-Robert Müller,et al.  SchNet: A continuous-filter convolutional neural network for modeling quantum interactions , 2017, NIPS.

[24]  Yang Yang,et al.  Deep Learning Scaling is Predictable, Empirically , 2017, ArXiv.

[25]  J S Smith,et al.  ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost , 2016, Chemical science.

[26]  E Weinan,et al.  End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems , 2018, NeurIPS.

[27]  Adrian E. Roitberg,et al.  Less is more: sampling chemical space with active learning , 2018, The Journal of chemical physics.

[28]  E Weinan,et al.  Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics , 2017, Physical review letters.

[29]  Thomas F. Miller,et al.  Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis. , 2018, Journal of chemical theory and computation.

[30]  Lin Lin,et al.  Disentanglement via Entanglement: A Unified Method for Wannier Localization , 2018, Multiscale Model. Simul..

[31]  Sandeep Sharma,et al.  PySCF: the Python‐based simulations of chemistry framework , 2018 .

[32]  Kipton Barros,et al.  Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning , 2019, Nature Communications.

[33]  Thomas F. Miller,et al.  Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning , 2019, Journal of chemical theory and computation.

[34]  E Weinan,et al.  Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation , 2018, Physical Review Materials.

[35]  Benjamin P Pritchard,et al.  New Basis Set Exchange: An Open, Up-to-Date Resource for the Molecular Sciences Community , 2019, J. Chem. Inf. Model..

[36]  Thomas F. Miller,et al.  A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules , 2019, The Journal of chemical physics.

[37]  Justin S. Smith,et al.  The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules , 2020, Scientific Data.

[38]  Sebastian Dick,et al.  Machine learning accurate exchange and correlation functionals of the electronic density , 2020, Nature Communications.

[39]  E Weinan,et al.  86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy , 2020, Comput. Phys. Commun..