Quantum Machine Learning using Gaussian Processes with Performant Quantum Kernels

Abstract

Quantum computers have the opportunity to be transformative for a variety of computational tasks. Recently, there have been proposals to use the unsimulatably of large quantum devices to perform regression, classification, and other machine learning tasks with quantum advantage by using kernel methods. While unsimulatably is a necessary condition for quantum advantage in machine learning, it is not sufficient, as not all kernels are equally effective. Here, we study the use of quantum computers to perform the machine learning tasks of one- and multi-dimensional regression, as well as reinforcement learning, using Gaussian Processes. By using approximations of performant classical kernels enhanced with extra quantum resources, we demonstrate that quantum devices, both in simulation and on hardware, can perform machine learning tasks at least as well as, and many times better than, the classical inspiration. Our informed kernel design demonstrates a path towards effectively utilizing quantum devices for machine learning tasks.

References in corpus (21)

• Scikit-learn: Machine Learning in Python
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• QuTiP 2: A Python framework for the dynamics of open quantum systems
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Error mitigation for short-depth quantum circuits
• Extending the computational reach of a noisy superconducting quantum processor
• Deep Neural Networks as Gaussian Processes
• Robust determination of molecular spectra on a quantum processor
• Efficient Classical Simulation of Continuous Variable Quantum Information Processes
• Monte Carlo Implementation of Gaussian Process Models for Bayesian Regression and Classification
• Photon State Tomography for Two-Mode Correlated Itinerant Microwave Fields
• Experimental generation of four-mode continuous-variable cluster states
• Distillation of the two-mode squeezed state
• Recovering noise-free quantum observables
• Noise-Resilient Quantum Dynamics Using Symmetry-Preserving Ansatzes
• Holomorphic Methods in Mathematical Physics

Cited by in corpus (5)

• Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials
• Optimal training of variational quantum algorithms without barren plateaus
• Impacts of Noise and Structure on Quantum Information Encoded in a Quantum Memory
• Quantum Gaussian process model of potential energy surface for a polyatomic molecule
• Faster variational quantum algorithms with quantum kernel-based surrogate models