Certainty In, Certainty Out: REVQCs for Quantum Machine Learning
This addresses a key bottleneck in quantum machine learning for researchers seeking practical quantum advantages, though it appears incremental as it builds on existing variational quantum circuits.
The paper tackles the challenge of achieving high single-sample accuracy in quantum machine learning by proposing reversed training for variational quantum circuits, demonstrating a 10-15% accuracy improvement on MNIST and Fashion MNIST subsets.
The field of Quantum Machine Learning (QML) has emerged recently in the hopes of finding new machine learning protocols or exponential speedups for classical ones. Apart from problems with vanishing gradients and efficient encoding methods, these speedups are hard to find because the sampling nature of quantum computers promotes either simulating computations classically or running them many times on quantum computers in order to use approximate expectation values in gradient calculations. In this paper, we make a case for setting high single-sample accuracy as a primary goal. We discuss the statistical theory which enables highly accurate and precise sample inference, and propose a method of reversed training towards this end. We show the effectiveness of this training method by assessing several effective variational quantum circuits (VQCs), trained in both the standard and reversed directions, on random binary subsets of the MNIST and MNIST Fashion datasets, on which our method provides an increase of $10-15\%$ in single-sample inference accuracy.