Fast evaluation of interaction integrals for confined systems with machine learning
arXiv:2007.12875 · doi:10.1103/PhysRevB.102.075422
Abstract
The calculation of interaction integrals is a bottleneck for the treatment of many-body quantum systems due to its high numerical cost. We conduct configuration interaction calculations of the few-electron states confined in III-V semiconductor 2D structures using a shallow neural network to calculate the two-electron integrals, that can be used for general isotropic interaction potentials. This approach allows for a speed up of the evaluation of the energy levels and a controllable accuracy.
arXiv comment9 pages, 10 figures
References in corpus (16)
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- Dielectric screening in two-dimensional insulators: Implications for excitonic and impurity states in graphane
- A Transferable Machine-Learning Model of the Electron Density
- Self-Learning Monte Carlo Method
- Efficient solution of Poisson's equation with free boundary conditions
- Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
- Approximating quantum many-body wave-functions using artificial neural networks
- Full configuration interaction approach to the few-electron problem in artificial atoms
- Constructing exact representations of quantum many-body systems with deep neural networks
- Self-learning Monte Carlo with Deep Neural Networks
- Self-Learning Monte Carlo Method: Continuous-Time Algorithm
- Spatial ordering of charge and spin in quasi one-dimensional Wigner molecules
- Calculation of two-centre two-electron integrals over Slater-type orbitals revisited. I. Coulomb and hybrid integrals
- Accurate and efficient computation of nonlocal potentials based on Gaussian-sum approximation
- Quantum neural networks to simulate many-body quantum systems
- Machine learning effective models for quantum systems