Tomography and generative training with quantum Boltzmann machines

Mária Kieferová, Nathan Wiebe

    Research output: Contribution to journalArticlepeer-review

    59 Citations (Scopus)

    Abstract

    The promise of quantum neural nets, which utilize quantum effects to model complex data sets, has made their development an aspirational goal for quantum machine learning and quantum computing in general. Here we provide methods of training quantum Boltzmann machines. Our work generalizes existing methods and provides additional approaches for training quantum neural networks that compare favorably to existing methods. We further demonstrate that quantum Boltzmann machines enable a form of partial quantum state tomography that further provides a generative model for the input quantum state. Classical Boltzmann machines are incapable of this. This verifies the long-conjectured connection between tomography and quantum machine learning. Finally, we prove that classical computers cannot simulate our training process in general unless BQP=BPP, provide lower bounds on the complexity of the training procedures and numerically investigate training for small nonstoquastic Hamiltonians.

    Original languageEnglish
    Article number062327
    Pages (from-to)1-13
    Number of pages13
    JournalPhysical Review A
    Volume96
    Issue number6
    DOIs
    Publication statusPublished - 22 Dec 2017

    Fingerprint

    Dive into the research topics of 'Tomography and generative training with quantum Boltzmann machines'. Together they form a unique fingerprint.

    Cite this