2020/06/10 by Christa Zoufal, Aurélien Lucchi, Stefan Woerner · 98 citations
Computer Science · Physics and Astronomy · #Artificial intelligence #Artificial neural network #Boltzmann constant #Boltzmann machine #Computer science #Generative Adversarial Networks and Image Synthesis #Model Reduction and Neural Networks #Neural Networks and Reservoir Computing #Physics #Quantum #Quantum mechanics #Statistical physics #Theoretical physics #quant-ph
paper · pdf · doi:10.1007/s42484-020-00033-7
published in Quantum Machine Intelligence 3(1) (Springer Science+Business Media)
arxiv created 2020/06/10 · openalex publication_date 2021/02/22 · arxiv updated 2021/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Abstract This work presents a novel realization approach to quantum Boltzmann machines (QBMs). The preparation of the required Gibbs states, as well as the evaluation of the loss function’s analytic gradient, is based on variational quantum imaginary time evolution, a technique that is typically used for ground-state computation. In contrast to existing methods, this implementation facilitates near-term compatible QBM training with gradients of the actual loss function for arbitrary parameterized Hamiltonians which do not necessarily have to be fully visible but may also include hidden units. The variational Gibbs state approximation is demonstrated with numerical simulations and experiments run on real quantum hardware provided by IBM Quantum. Furthermore, we illustrate the application of this variational QBM approach to generative and discriminative learning tasks using numerical simulation.