Solving many-electron Schrödinger equation using deep neural networks

We introduce a new family of trial wave-functions based on deep neural networks to solve the many-electron Schrodinger equation. The Pauli exclusion principle is dealt with explicitly to ensure that the trial wave-functions are physical. The optimal trial wave-function is obtained through variational Monte Carlo and the computational cost scales quadratically with the number of electrons. The algorithm does not make use of any prior knowledge such as atomic orbitals. Yet it is able to represent accurately the ground-states of the tested systems, including He, H2, Be, B, LiH, and a chain of 10 hydrogen atoms. This opens up new possibilities for solving large-scale many-electron Schrodinger equation.

[1]  Richard L. Martin,et al.  Ab initio quantum chemistry using the density matrix renormalization group , 1998 .

[2]  Garnet Kin-Lic Chan,et al.  Density Matrix Embedding: A Strong-Coupling Quantum Embedding Theory. , 2012, Journal of chemical theory and computation.

[3]  P. Dirac.  Quantum Mechanics of Many-Electron Systems , 1929 .

[4]  Arnulf Jentzen,et al.  Solving high-dimensional partial differential equations using deep learning , 2017, Proceedings of the National Academy of Sciences.

[5]  Linfeng Zhang,et al.  DeePCG: Constructing coarse-grained models via deep neural networks. , 2018, The Journal of chemical physics.

[6]  Johannes Grotendorst,et al.  Modern methods and algorithms of quantum chemistry , 2000 .

[7]  R. Sugar,et al.  Monte Carlo calculations of coupled boson-fermion systems. I , 1981 .

[8]  C. C. J. Roothaan,et al.  Self-Consistent Field Theory for Open Shells of Electronic Systems , 1960 .

[9]  J. E. Gubernatis,et al.  Constrained path Monte Carlo method for fermion ground states , 1997 .

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

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  W. Pauli,et al.  Über den Zusammenhang des Abschlusses der Elektronengruppen im Atom mit der Komplexstruktur der Spektren , 1925 .

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

[14]  R. Jastrow.  Many-Body Problem with Strong Forces , 1955 .

[15]  Kris Van Houcke,et al.  Diagrammatic Monte Carlo , 2008, 0802.2923.

[16]  Isaiah Shavitt,et al.  Many-Body Methods in Chemistry and Physics: MBPT and Coupled-Cluster Theory , 2009 .

[17]  J. Pople,et al.  Self‐Consistent Molecular‐Orbital Methods. I. Use of Gaussian Expansions of Slater‐Type Atomic Orbitals , 1969 .

[18]  Henry Krakauer,et al.  Quantum Monte Carlo method using phase-free random walks with slater determinants. , 2003, Physical review letters.

[19]  Garnet Kin-Lic Chan,et al.  Matrix product operators, matrix product states, and ab initio density matrix renormalization group algorithms. , 2016, The Journal of chemical physics.

[20]  R. Laughlin.  Anomalous quantum Hall effect: An incompressible quantum fluid with fractionally charged excitations , 1983 .

[21]  David M. Ceperley,et al.  Towards the solution of the many-electron problem in real materials: equation of state of the hydrogen chain with state-of-the-art many-body methods , 2017, 1705.01608.

[22]  P. Knowles,et al.  An efficient internally contracted multiconfiguration–reference configuration interaction method , 1988 .

[23]  Kaj Nyström,et al.  A unified deep artificial neural network approach to partial differential equations in complex geometries , 2017, Neurocomputing.

[24]  Nakatsuka,et al.  Excess-path-length distribution of fast charged particles. , 1987, Physical review. D, Particles and fields.

[25]  Lexing Ying,et al.  Solving parametric PDE problems with artificial neural networks , 2017, European Journal of Applied Mathematics.

[26]  Toru Shiozaki,et al.  Explicitly correlated multireference configuration interaction: MRCI-F12. , 2011, The Journal of chemical physics.

[27]  A. Szabó,et al.  Modern quantum chemistry : introduction to advanced electronic structure theory , 1982 .

[28]  H. Saito.  Solving the Bose–Hubbard Model with Machine Learning , 2017, 1707.09723.

[29]  Sandro Sorella,et al.  Geminal wave functions with Jastrow correlation: A first application to atoms , 2003 .

[30]  Garnet Kin-Lic Chan,et al.  Density matrix embedding: a simple alternative to dynamical mean-field theory. , 2012, Physical review letters.

[31]  Hiroki Saito,et al.  Method to Solve Quantum Few-Body Problems with Artificial Neural Networks , 2018, Journal of the Physical Society of Japan.

[32]  小谷 正雄.  日本物理学会誌及びJournal of the Physical Society of Japanの月刊について , 1955 .

[33]  John C. Slater,et al.  Note on Hartree's Method , 1930 .

[34]  J. Cirac,et al.  Neural-Network Quantum States, String-Bond States, and Chiral Topological States , 2017, 1710.04045.

[35]  W. Heisenberg,et al.  Zur Quantentheorie der Molekeln , 1924 .

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

[38]  Abraham Robinson,et al.  COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS , 1956 .

[39]  N. Nemec,et al.  Strategies for improving the efficiency of quantum Monte Carlo calculations. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[40]  Richard G. Hennig,et al.  Alleviation of the Fermion-sign problem by optimization of many-body wave functions , 2007 .

[41]  P. Knowles,et al.  An efficient method for the evaluation of coupling coefficients in configuration interaction calculations , 1988 .

[42]  R. Bartlett,et al.  A full coupled‐cluster singles and doubles model: The inclusion of disconnected triples , 1982 .

[43]  Josef Paldus,et al.  A Critical Assessment of Coupled Cluster Method in Quantum Chemistry , 2007 .

[44]  C. Pekeris,et al.  Logarithmic Terms in the Wave Functions of the Ground State of Two-Electron Atoms , 1966 .

[45]  White,et al.  Density matrix formulation for quantum renormalization groups. , 1992, Physical review letters.

[46]  R. K. Nesbet,et al.  Self‐Consistent Orbitals for Radicals , 1954 .

[47]  Thom H. Dunning,et al.  Gaussian basis sets for use in correlated molecular calculations. V. Core-valence basis sets for boron through neon , 1995 .

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

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

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

[51]  W. L. Mcmillan.  Ground State of Liquid He 4 , 1965 .

[52]  Jinguo Liu,et al.  Approximating quantum many-body wave functions using artificial neural networks , 2017, 1704.05148.

[53]  S. R. Clark,et al.  Unifying neural-network quantum states and correlator product states via tensor networks , 2017, 1710.03545.

[54]  E Weinan,et al.  Reinforced dynamics for enhanced sampling in large atomic and molecular systems. I. Basic Methodology , 2017, The Journal of chemical physics.

[55]  Dario Bressanini,et al.  Between Classical and Quantum Monte Carlo Methods: Variational QMC , 2007 .

[56]  M. Head‐Gordon,et al.  Highly correlated calculations with a polynomial cost algorithm: A study of the density matrix renormalization group , 2002 .

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

[58]  T. H. Dunning.  Gaussian basis sets for use in correlated molecular calculations. I. The atoms boron through neon and hydrogen , 1989 .

[59]  Mark Dewing.  Improved efficiency with variational Monte Carlo using two level sampling , 2000 .

[60]  Mark E Tuckerman,et al.  Stochastic Neural Network Approach for Learning High-Dimensional Free Energy Surfaces. , 2017, Physical review letters.

[61]  Tosio Kato,et al.  On the Eigenfunctions of Many-Particle Systems in Quantum Mechanics , 2011 .

[62]  Lu-Ming Duan,et al.  Efficient representation of quantum many-body states with deep neural networks , 2017, Nature Communications.

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

[64]  Qiming Sun,et al.  A Practical Guide to Density Matrix Embedding Theory in Quantum Chemistry. , 2016, Journal of chemical theory and computation.

[65]  Wilson,et al.  Optimized trial wave functions for quantum Monte Carlo calculations. , 1988, Physical review letters.

[66]  Steven R White,et al.  Sliced Basis Density Matrix Renormalization Group for Electronic Structure. , 2017, Physical review letters.

[67]  D. Ceperley,et al.  Monte Carlo simulation of a many-fermion study , 1977 .

[68]  Matthias Troyer,et al.  Solving the quantum many-body problem with artificial neural networks , 2016, Science.

[69]  R. Needs,et al.  Quantum Monte Carlo simulations of solids , 2001 .

[70]  R. Bartlett,et al.  Coupled-cluster theory in quantum chemistry , 2007 .

[71]  E Weinan,et al.  Deep Learning-Based Numerical Methods for High-Dimensional Parabolic Partial Differential Equations and Backward Stochastic Differential Equations , 2017, Communications in Mathematics and Statistics.

[72]  Garnet Kin-Lic Chan,et al.  Approximating strongly correlated wave functions with correlator product states , 2009, 0907.4646.