Quantum Parallel Training of a Boltzmann Machine on an Adiabatic Quantum Computer

Abstract

Despite the anticipated speed-up of quantum computing, the achievement of a measurable advantage remains subject to ongoing debate. Adiabatic Quantum Computers (AQCs) are quantum devices designed to solve quadratic uncostrained binary optimization (QUBO) problems, but their intrinsic thermal noise can be leveraged to train computationally demanding machine learning algorithms such as the Boltzmann Machine (BM). Despite an asymptotic advantage is expected only for large networks, a limited quantum speed up can be already achieved on a small $16\times 16$ BM is shown, by exploiting parallel adiabatic computation. This approach exhibits a 8.6-fold improvement in wall time on the $4\times 4$ Bars and Stripes dataset when compared to a parallelized classical Gibbs sampling method, which has never been outperformed before by quantum approaches.