Improving the performance of fermionic neural networks with the Slater exponential Ansatz

Abstract

In this work, we propose a technique for the use of fermionic neural networks (FermiNets) with the Slater exponential Ansatz for electron-nuclear and electron-electron distances, which provides faster convergence of target ground-state energies due to a better description of the interparticle interaction in the vicinities of the coalescence points. Analysis of learning curves indicates on the possibility to obtain accurate energies with smaller batch sizes using arguments of the bagging approach. In order to obtain even more accurate results for the ground-state energies, we suggest an extrapolation scheme, which estimates Monte Carlo integrals in the limit of an infinite number of points. Numerical tests for a set of molecules demonstrate a good agreement with the results of original FermiNets (achieved with larger batch sizes than required by our approach) and with results of coupled-cluster singles and doubles with perturbative triples (CCSD(T)) method, calculated in the complete basis set (CBS) limit.

arXiv comment11 pages, 2 figures, 1 table

References in corpus (12)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Quantum computational chemistry
• Quantum Chemistry in the Age of Quantum Computing
• Quantum algorithms for quantum chemistry and quantum materials science
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Reconstructing quantum states with generative models
• Fermionic neural-network states for ab-initio electronic structure
• Pfaffian pairing wave functions in electronic structure quantum Monte Carlo
• Quantum Machine Learning for Electronic Structure Calculations