Programmable Photonic Simulator for Spin Glass Models

Abstract

Spin glasses featured by frustrated interactions and metastable states have important applications in chemistry, material sciences and artificial neural networks. However, the solution of the spin glass models is hindered by the computational complexity that exponentially increases with the sample size. Photonic Ising machines based on spatial light modulation can speed up the calculation by obtaining the Hamiltonian from the modulated light intensity. However, the large-scale generalization to various spin couplings and higher dimensions is still elusive. Here, we develop a Fourier-mask method to program the spin couplings in photonic Ising machines. We observe the phase transition of the two-dimensional Mattis model and the J$\mathrm{_1}$-J$\mathrm{_2}$ model and study the critical phenomena. We also demonstrate that the three-dimensional Ising model, which has not been analytically solved, can be effectively constructed and simulated in two-dimensional lattices with Fourier masks. Our strategy provides a flexible route to tuning couplings and dimensions of statistical spin models, and improves the applicability of optical simulation in neural networks and combinatorial optimization problems.