Abstract
Data representation is crucial for the success of machine-learning models. In the context of quantum machine learning with near-term quantum computers, equally important considerations of how to efficiently input (encode) data and effectively deal with noise arise. In this paper, we study data encodings for binary quantum classification and investigate their properties both with and without noise. For the common classifier we consider, we show that encodings determine the classes of learnable decision boundaries as well as the set of points which retain the same classification in the presence of noise. After defining the notion of a robust data encoding, we prove several results on robustness for different channels, discuss the existence of robust encodings, and prove a lower bound on the number of robust points in terms of fidelities between noisy and noiseless states. Numerical results for several example implementations are provided to reinforce our findings.
7 More- Received 7 April 2020
- Accepted 24 August 2020
- Corrected 1 October 2020
DOI:https://doi.org/10.1103/PhysRevA.102.032420
©2020 American Physical Society
Physics Subject Headings (PhySH)
Corrections
1 October 2020
Correction: An error in wording in the penultimate sentence of the abstract has been fixed.