Robust data encodings for quantum classifiers
By Ryan Larose, Brian Coyle. Physical Review A, 2020
340 citations recorded by the source corpus.
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 work, 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 an upper 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.
Subfields: Artificial Intelligence, Atomic and Molecular Physics, and Optics
View Paper: https://www.semanticscholar.org/paper/5ddb6dbb1ac160ac256b21cf12d4cc383f1aa482
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- M. Cerezo
- Patrick J. Coles
- Lukasz Cincio
- Hsin-Yuan Huang
- Guillaume Verdon
- L. Kim
- Tak Hur
- Daniel K. Park
In Atomic and Molecular Physics, and Optics
- M. Cerezo
- Lukasz Cincio
- Patrick J. Coles
- L. Kim
- Tak Hur
- Daniel K. Park
- Hsin-Yuan Huang
- Guillaume Verdon
Citations in the corpus
- Quantum convolutional neural network for classical data classification (2021, methodology): “Thus the qubit encoding described above can be generalized to encode two classical vectors per qubit by using rotations around two orthogonal axes [39].”
- Effect of data encoding on the expressive power of variational quantum-machine-learning models (2020, background): “[25] Ryan LaRose and Brian Coyle, “Robust data encodings for quantum classifiers,” arXiv preprint arXiv:2003.”
- Challenges and opportunities in quantum machine learning (2022, background): “A different approach to dealing with noise is to engineer QML models with noise-resilient properties [34, 104, 105] (such as the position of the minima not changing due to noise).”