Quantum adiabatic machine learning with zooming

TL;DR

This paper introduces QAML-Z, a quantum annealing-based machine learning algorithm that iteratively refines its focus on the problem space, achieving performance comparable to deep neural networks and narrowing the gap at larger training sizes.

Contribution

QAML-Z is a novel quantum annealing algorithm that maps to a continuous space and sequentially applies quantum annealing to improve machine learning performance.

Findings

QAML-Z matches deep neural network performance at small training sizes.

QAML-Z reduces the performance gap with classical methods by nearly 50% at large training sizes.

Quantum annealing algorithms can effectively solve continuous optimization problems in machine learning.

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.