Quantum adiabatic machine learning with zooming
This work addresses the performance gap between quantum and classical machine learning methods, particularly for classification tasks like Higgs boson detection, though it appears incremental as it builds on prior QAML work.
The authors tackled the problem of improving quantum annealing for machine learning by proposing QAML-Z, an algorithm that iteratively zooms in on energy surfaces using quantum annealing on augmented weak classifiers, resulting in matching classical deep neural network performance at small training set sizes and reducing the performance gap by almost 50% at large sizes as measured by area under the ROC curve.
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.