Unifying view of fermionic neural network quantum states: From neural network backflow to hidden fermion determinant states
- 12 September 2024
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review B
- Vol. 110 (11) , 115124
Abstract
Among the variational wave functions for fermionic Hamiltonians, neural network backflow (NNBF) and hidden fermion determinant states (HFDS) are two prominent classes that provide accurate approximations to the ground state. Here we develop a unifying view of fermionic neural quantum states casting them all in the framework of NNBF. NNBF wave functions have configuration-dependent single-particle orbitals (SPO) which are parameterized by a neural network. We show that HFDS can be written as a NNBF wave function with a restricted low-rank additive correction to the SPO times a neural-network generated determinant of an matrix. Furthermore, we show that in NNBF wave functions, this determinant can generically be removed when is less than or equal to the number of fermions, at the cost of further complicating the additive SPO correction increasing its rank by . We numerically and analytically compare additive SPO corrections generated by the product of two matrices with inner dimension . We find that larger wave functions span a larger space and give evidence that simpler and more direct updates to the SPO's tend to be more expressive and better energetically. These suggest the standard NNBF approach is preferred amongst other related choices. Finally, we uncover that the row selection used to select single-particle orbitals allows significant sign and amplitude modulation between nearby configurations and is partially responsible for the quality of NNBF and HFDS wave functions.
Keywords
All Related Versions
Funding Information
- University of Illinois at Urbana-Champaign
- National Science Foundation (2016136)
This publication has 35 references indexed in Scilit:
- Ab initio quantum chemistry with neural-network wavefunctionsNature Reviews Chemistry, 2023
- Fermionic wave functions from neural-network constrained hidden statesProceedings of the National Academy of Sciences, 2022
- Solving quasiparticle band spectra of real solids using neural-network quantum statesCommunications Physics, 2021
- Deep-neural-network solution of the electronic Schrödinger equationNature Chemistry, 2020
- Fermionic neural-network states for ab-initio electronic structureNature Communications, 2020
- Variational and diffusion quantum Monte Carlo calculations with the CASINO codeThe Journal of Chemical Physics, 2020
- Tensor networks for complex quantum systemsNature Reviews Physics, 2019
- A practical introduction to tensor networks: Matrix product states and projected entangled pair statesAnnals of Physics, 2014
- Ground-state properties of quantum many-body systems: entangled-plaquette states and variational Monte CarloNew Journal of Physics, 2009
- Approximation theory of the MLP model in neural networksActa Numerica, 1999