Non-Classical Kernels in Continuous Variable Systems

Kernel methods are ubiquitous in classical machine learning, and recently their formal similarity with quantum mechanics has been established. To grasp the potential advantage of quantum machine learning, it is necessary to understand the distinction between non-classical kernel functions and classical kernels. This paper builds on a recently proposed phase space nonclassicality witness [Bohmann, Agudelo, Phys. Rev. Lett. 124, 133601 (2020)] to derive a witness for the kernels quantumness in continuous-variable systems. We discuss the role of kernels nonclassicality in data distribution in the feature space and the effect of imperfect state preparation. Furthermore, we show that the non-classical kernels lead to the quantum advantage in parameter estimation. Our work highlights the role of the phase space correlation functions in understanding the distinction between classical machine learning from quantum machine learning.