Polynomial unconstrained binary optimisation inspired by optical simulation

Abstract

We propose an algorithm inspired by optical coherent Ising machines to solve the problem of polynomial unconstrained binary optimization (PUBO). We benchmark the proposed algorithm against existing PUBO algorithms on the extended Sherrington-Kirkpatrick model and random third-degree polynomial pseudo-Boolean functions, and observe its superior performance. We also address instances of practically relevant computational problems such as protein folding and electronic structure calculations with problem sizes not accessible to existing quantum annealing devices. The application of our algorithm to protein folding and quantum chemistry problems sheds light on the shortcomings of approximating the electronic structure problem by a PUBO problem, which, in turn, puts into question the applicability of the unconstrained binary optimization formulation, such as that of quantum annealers and coherent Ising machines, in this context.