Quantum adiabatic machine learning with zooming

ORAL

Abstract

Recent work has shown that quantum annealing for machine learning, referred to as QAML, can perform comparably to state-of-the-art machine learning methods with a specific application to Higgs boson classification. We propose QAML-Z, a novel algorithm that iteratively zooms in on a region of the energy surface by mapping the problem to a continuous space and sequentially applying quantum annealing to an augmented set of weak classifiers. Results on a programmable quantum annealer show that QAML-Z matches classical deep neural network performance at small training set sizes and reduces the performance margin between QAML and classical deep neural networks by almost 50% at large training set sizes, as measured by area under the ROC curve. The significant improvement of quantum annealing algorithms for machine learning and the use of a discrete quantum algorithm on a continuous optimization problem both opens a new class of problems that can be solved by quantum annealers and suggests the approach in performance of near-term quantum machine learning towards classical benchmarks.

*DOE/HEP QuantISED program grant, QMLQCF for HEP, DE-SC0019227. AT&T Foundry Innovation Centers, INQNET. ODNI and IARPA via U.S. Army Research Office contract W911NF-17-C-0050.

Presenters

  • Jean-Roch Vlimant

    • Caltech

Authors

  • Alexander Zlokapa

    • Caltech
  • Alex Mott

    • DeepMind Technologies
  • Joshua Job

    • Lockheed Martin
  • Jean-Roch Vlimant

    • Caltech
  • Daniel Lidar

    • Univ of Southern California
    • University of Southern California
  • Maria Spiropulu

    • Caltech