Artificial Intelligence for Quantum Matter: Finding a Needle in a Haystack
Published: Jul 17, 2025
Last Updated: Jul 17, 2025
Authors:Khachatur Nazaryan, Filippo Gaggioli, Yi Teng, Liang Fu
Abstract
Neural networks (NNs) have great potential in solving the ground state of various many-body problems. However, several key challenges remain to be overcome before NNs can tackle problems and system sizes inaccessible with more established tools. Here, we present a general and efficient method for learning the NN representation of an arbitrary many-body complex wave function. Having reached overlaps as large as $99.9\%$ for as many as $25$ particles, we employ our neural wave function for pre-training to effortlessly solve the fractional quantum Hall problem for $20$ electrons with Coulomb interactions and realistic Landau-level mixing.