Quantum-inspired annealers as Boltzmann generators for machine learning and statistical physics
This work provides a practical tool for machine learning and statistical physics researchers, though it is incremental as it applies an existing quantum-inspired method to a specific sampling task.
The authors tackled the problem of sampling from high-dimensional Boltzmann distributions by implementing a numerical annealer based on simulating a coherent Ising machine, achieving efficient sampling for partition function estimation and training of Boltzmann machines.
Quantum simulators and processors are rapidly improving nowadays, but they are still not able to solve complex and multidimensional tasks of practical value. However, certain numerical algorithms inspired by the physics of real quantum devices prove to be efficient in application to specific problems, related, for example, to combinatorial optimization. Here we implement a numerical annealer based on simulating the coherent Ising machine as a tool to sample from a high-dimensional Boltzmann probability distribution with the energy functional defined by the classical Ising Hamiltonian. Samples provided by such a generator are then utilized for the partition function estimation of this distribution and for the training of a general Boltzmann machine. Our study opens up a door to practical application of numerical quantum-inspired annealers.