Quantum Boltzmann Machine

2016/01/08 by Mohammad H. Amin, Evgeny Andriyash, Jason Rolfe +2 · 3 citations
Physics and Astronomy · #quant-ph

paper · pdf · doi:10.1103/physrevx.8.021050

published as Phys. Rev. X 8, 021050 (2018) · 10 pages, 4 figures

arxiv created 2016/01/08 · arxiv updated 2018/05/30

Abstract

Inspired by the success of Boltzmann Machines based on classical Boltzmann distribution, we propose a new machine learning approach based on quantum Boltzmann distribution of a transverse-field Ising Hamiltonian. Due to the non-commutative nature of quantum mechanics, the training process of the Quantum Boltzmann Machine (QBM) can become nontrivial. We circumvent the problem by introducing bounds on the quantum probabilities. This allows us to train the QBM efficiently by sampling. We show examples of QBM training with and without the bound, using exact diagonalization, and compare the results with classical Boltzmann training. We also discuss the possibility of using quantum annealing processors like D-Wave for QBM training and application.

Cited by

• Model selection in hybrid quantum neural networks with applications to quantum transformer architectures
• Unifying quantum measurement constructions via a relative-entropy minimum change principle
• Speedup Chip Yield Analysis by Improved Quantum Bayesian Inference