Pith. sign in

Quantum adiabatic machine learning with zooming

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

fields

hep-ph 1

years

2019 1

verdicts

ACCEPT 1

representative citing papers

Quantum Algorithms for Jet Clustering

hep-ph · 2019-08-23 · accept · novelty 7.0

Thrust can be computed in O(N^2) time with a Grover-based quantum algorithm under a sequential data-loading model, and in O(N^2 log N) time classically with sorting, but the quantum advantage is only formal for very restrictive memory models.

citing papers explorer

Showing 1 of 1 citing paper.

  • Quantum Algorithms for Jet Clustering hep-ph · 2019-08-23 · accept · none · ref 65 · internal anchor

    Thrust can be computed in O(N^2) time with a Grover-based quantum algorithm under a sequential data-loading model, and in O(N^2 log N) time classically with sorting, but the quantum advantage is only formal for very restrictive memory models.