A hybrid quantum-classical approach for inference on restricted Boltzmann machines
This work addresses sampling bottlenecks in machine learning models like Boltzmann machines, but it is incremental due to limited quantum performance.
The authors tackled the problem of sampling from restricted Boltzmann machines by using a hybrid quantum-classical approach with a D-Wave quantum annealer, demonstrating that it improves Gibbs sampling efficiency compared to random initialization, though benefits diminish with more classical processing.
Boltzmann machine is a powerful machine learning model with many real-world applications, for example by constructing deep belief networks. Statistical inference on a Boltzmann machine can be carried out by sampling from its posterior distribution. However, uniform sampling from such a model is not trivial due to an extremely multi-modal distribution. Quantum computers have the promise of solving some non-trivial problems in an efficient manner. We explored the application of a D-Wave quantum annealer to generate samples from a restricted Boltzmann machine. The samples are further improved by Markov chains in a hybrid quantum-classical setup. We demonstrated that quantum annealer samples can improve the performance of Gibbs sampling compared to random initialization. The hybrid setup is considerably more efficient than a pure classical sampling. We also investigated the impact of annealing parameters (temperature) to improve the quality of samples. By increasing the amount of classical processing (Gibbs updates) the benefit of quantum annealing vanishes, which may be justified by the limited performance of today's quantum computers compared to classical.