Speaker
Description
The Hamiltonian formulation of lattice gauge theories solves several of the problems in Euclidean Monte Carlo simulations. However, the main obstacle is the exponential growth of the Hilbert space with the lattice volume, and one needs to find an effective representation that fits the computer memory. Most of the present calculations rely on explicit truncation methods, usually suited only for a fixed region of the coupling. In this talk I present a new approach based on Physics-Informed Neural Networks (PINNs), where the wavefunction is parametrised by a neural network and the eigenvalue problem is encoded in the loss function. By training at progressively weaker couplings, PINNs allow to move along the renormalization flow of the theory. This is achieved using an adiabatic training strategy, seeded from the analytically known strong-coupling eigenstates.