Solving Schrodinger equations using physically constrained neural network

Abstract

Deep neural network (DNN) and auto differentiation have been widely used in computational physics to solve variational problems. When DNN is used to represent the wave function to solve quantum many-body problems using variational optimization, various physical constraints have to be injected into the neural network by construction, to increase the data and learning efficiency. We build the unitary constraint to the variational wave function using a monotonic neural network to represent the Cumulative Distribution Function (CDF) $F(x)={\int }_{-\infty }^x{\psi }^{\ast }\psi d{x}^{\prime }$. Using this constrained neural network to represent the variational wave function, we solve Schrodinger equations using auto-differentiation and stochastic gradient descent (SGD), by minimizing the violation of the trial wave function $\psi (x)$ to the Schrodinger equation. For several classical problems in quantum mechanics, we obtain their ground state wave function and energy with very low errors. The method developed in the present paper may pave a new way in solving nuclear many body problems in the future.

References in corpus (16)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A high-bias, low-variance introduction to Machine Learning for physicists
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Machine Learning in Nuclear Physics
• Fermionic neural-network states for ab-initio electronic structure
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Variational Monte Carlo calculations of $\mathbf{A}\le 4$ nuclei with an artificial neural-network correlator ansatz
• Machine learning the deuteron
• Heavy quark potential in quark-gluon Plasma: Deep neural network meets lattice quantum chromodynamics
• Nonlinear Network description for many-body quantum systems in continuous space
• Method to solve quantum few-body problems with artificial neural networks
• Gauge equivariant neural networks for quantum lattice gauge theories
• Fourier-Flow model generating Feynman paths
• Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
• Remarks on the Woods-Saxon Potential

Cited by in corpus (1)

• Decay of superheavy nuclei based on the random forest algorithm