A machine learning perspective on microscopic models for materials: Hamiltonian learning and simulation using neural quantum states

Following the discovery of high temperature superconductivity, unraveling its origins has become a key problem of condensed matter physics. From a model perspective, a wealth of research has concentrated on the paradigmatic plain vanilla Fermi-Hubbard model, which has been a key motivation for analog quantum simulation using fermionic atoms in optical lattices. 

In this talk, I will present our recent efforts, using theoretical considerations as well as Hamiltonian learning techniques, to determine simple models that may capture the physics of the cuprates. I will then show how we can numerically simulate models of interacting fermions, relevant for cuprates and nickelates, using neural quantum states.