Phase-space negativity as a computational resource for quantum kernel methods

Abstract

Quantum kernel methods are a proposal for achieving quantum computational advantage in machine learning. They are based on a hybrid classical-quantum computation where a function called the quantum kernel is estimated by a quantum device while the rest of computation is performed classically. Quantum advantages may be achieved through this method only if the quantum kernel function cannot be estimated efficiently on a classical computer. In this paper, we provide sufficient conditions for the efficient classical estimation of quantum kernel functions for bosonic systems. These conditions are based on phase-space properties of data-encoding quantum states associated with the quantum kernels: negative volume, non-classical depth, and excess range, which are shown to be three signatures of phase-space negativity. We consider quantum optical examples involving linear-optical networks with and without adaptive non-Gaussian measurements, and investigate the effects of loss on the efficiency of the classical simulation. Our results underpin the role of the negativity in phase-space quasi-probability distributions as an essential resource in quantum machine learning based on kernel methods.

References in corpus (38)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• Gaussian Quantum Information
• Quantum Simulation
• Supervised learning with quantum enhanced feature spaces
• Quantum machine learning in feature Hilbert spaces
• Kernel methods in machine learning
• Measurement-based quantum computation
• Negativity of the Wigner function as an indicator of nonclassicality
• Gaussian Boson Sampling
• Positive Wigner functions render classical simulation of quantum computation efficient
• Quantum advantage with shallow circuits
• A Coherent Ising Machine Based On Degenerate Optical Parametric Oscillators
• Negativity and contextuality are equivalent notions of nonclassicality
• Boson Sampling from Gaussian States
• Average-case complexity versus approximate simulation of commuting quantum computations
• Resource theory of quantum non-Gaussianity and Wigner negativity
• Estimating outcome probabilities of quantum circuits using quasiprobabilities
• Sufficient Conditions for Efficient Classical Simulation of Quantum Optics
• Frame representations of quantum mechanics and the necessity of negativity in quasi-probability representations
• Stellar representation of non-Gaussian quantum states
• Framed Hilbert space: hanging the quasi-probability pictures of quantum theory
• A quantum hardware-induced graph kernel based on Gaussian Boson Sampling
• What can quantum optics say about computational complexity theory?
• Programmable interference between two microwave quantum memories
• Efficient simulation scheme for a class of quantum optics experiments with non-negative Wigner representation
• Quantum phase space measurement and entanglement validation made easy
• Resources for bosonic quantum computational advantage
• Hybrid quantum computation gate with trapped ion system
• Quantum interference as a resource for quantum speedup
• Phase-space inequalities beyond negativities
• Quantum machine learning with adaptive linear optics
• Process output nonclassicality and nonclassicality depth of quantum-optical channels
• Holomorphic representation of quantum computations
• Quadrature coherence scale driven fast decoherence of bosonic quantum field states
• In situ characterization of linear-optical networks in randomized boson sampling
• Approximating outcome probabilities of linear optical circuits
• Swap-test interferometry with biased ancilla noise

Cited by in corpus (5)

• Quantum Kernel Machine Learning With Continuous Variables
• Nonclassical photocounting statistics with a single on-off detector
• Classical algorithms for measurement-adaptive Gaussian circuits
• Resourcefulness of non-classical continuous-variable quantum gates
• Latent optical nonclassicality of conditionally prepared states