Quantum Kernel Machine Learning With Continuous Variables

Abstract

The popular qubit framework has dominated recent work on quantum kernel machine learning, with results characterising expressivity, learnability and generalisation. As yet, there is no comparative framework to understand these concepts for continuous variable (CV) quantum computing platforms. In this paper we represent CV quantum kernels as closed form functions and use this representation to provide several important theoretical insights. We derive a general closed form solution for all CV quantum kernels and show every such kernel can be expressed as the product of a Gaussian and an algebraic function of the parameters of the feature map. Furthermore, in the multi-mode case, we present quantification of a quantum-classical separation for all quantum kernels via a hierarchical notion of the ``stellar rank" of the quantum kernel feature map. We then prove kernels defined by feature maps of infinite stellar rank, such as GKP-state encodings, can be approximated arbitrarily well by kernels defined by feature maps of finite stellar rank. Finally, we simulate learning with a single-mode displaced Fock state encoding and show that (i) accuracy on our specific task (an annular data set) increases with stellar rank, (ii) for underfit models, accuracy can be improved by increasing a bandwidth hyperparameter, and (iii) for noisy data that is overfit, decreasing the bandwidth will improve generalisation but does so at the cost of effective stellar rank.

23+26 pages, 7 figures

References in corpus (20)

• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Kernel methods in machine learning
• Power of data in quantum machine learning
• Quantum advantage in learning from experiments
• A rigorous and robust quantum speed-up in supervised machine learning
• Efficient Classical Simulation of Continuous Variable Quantum Information Processes
• Quantum machine learning beyond kernel methods
• Training Quantum Embedding Kernels on Near-Term Quantum Computers
• Resources for bosonic quantum computational advantage
• Covariant quantum kernels for data with group structure
• Certification of non-Gaussian states with operational measurements
• Classical simulation of Gaussian quantum circuits with non-Gaussian input states
• Structural risk minimization for quantum linear classifiers
• Causal Inference via Kernel Deviance Measures
• Holomorphic representation of quantum computations
• Numerical evidence against advantage with quantum fidelity kernels on classical data
• Phase-space negativity as a computational resource for quantum kernel methods
• Quantum Kernel Evaluation via Hong-Ou-Mandel Interference

Cited by in corpus (1)

• Quantum Algorithms for Causal Estimands