Non-Classical Kernels in Continuous Variable Systems
arXiv:2105.05990 · doi:10.1103/PhysRevA.104.052403
Abstract
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 kernel's quantumness in continuous-variable systems. We discuss the role of kernel's 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.
References in corpus (27)
- Supplementary information for "Quantum supremacy using a programmable superconducting processor"
- Quantum Machine Learning
- Supervised learning with quantum enhanced feature spaces
- Machine learning and the physical sciences
- Quantum computational advantage using photons
- Quantum machine learning in feature Hilbert spaces
- Kernel methods in machine learning
- The effect of data encoding on the expressive power of variational quantum machine learning models
- Power of data in quantum machine learning
- Contextuality supplies the magic for quantum computation
- Entanglement by a beam splitter: nonclassicality as a prerequisite for entanglement
- Quantum circuits with many photons on a programmable nanophotonic chip
- A rigorous and robust quantum speed-up in supervised machine learning
- Quantum speed limits in open system dynamics
- Discrete phase space based on finite fields
- Quantum Computing with Continuous-Variable Clusters
- Negativity and contextuality are equivalent notions of nonclassicality
- Blueprint for a Scalable Photonic Fault-Tolerant Quantum Computer
- Converting Nonclassicality into Entanglement
- Experimental quantum speed-up in reinforcement learning agents
- Phase space simulation method for quantum computation with magic states on qubits
- Quantum-enhanced data classification with a variational entangled sensor network
- Physical-Layer Supervised Learning Assisted by an Entangled Sensor Network
- Phase-space inequalities beyond negativities
- Quasiprobability distributions for quantum-optical coherence and beyond
- Probing nonclassicality with matrices of phase-space distributions
- Experimental certification of nonclassicality via phase-space inequalities