Quantum machine learning of large datasets using randomized measurements

Abstract

Quantum computers promise to enhance machine learning for practical applications. Quantum machine learning for real-world data has to handle extensive amounts of high-dimensional data. However, conventional methods for measuring quantum kernels are impractical for large datasets as they scale with the square of the dataset size. Here, we measure quantum kernels using randomized measurements. The quantum computation time scales linearly with dataset size and quadratic for classical post-processing. While our method scales in general exponentially in qubit number, we gain a substantial speed-up when running on intermediate-sized quantum computers. Further, we efficiently encode high-dimensional data into quantum computers with the number of features scaling linearly with the circuit depth. The encoding is characterized by the quantum Fisher information metric and is related to the radial basis function kernel. Our approach is robust to noise via a cost-free error mitigation scheme. We demonstrate the advantages of our methods for noisy quantum computers by classifying images with the IBM quantum computer. To achieve further speedups we distribute the quantum computational tasks between different quantum computers. Our method enables benchmarking of quantum machine learning algorithms with large datasets on currently available quantum computers.

15 pages, 11 figures, data for the experiments available at https://doi.org/10.5281/zenodo.5211695, code available at https://github.com/chris-n-self/large-scale-qml

References in corpus (18)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Strong quantum computational advantage using a superconducting quantum processor
• Hybrid quantum-classical algorithms and quantum error mitigation
• t$|$ket$⟩$ : A Retargetable Compiler for NISQ Devices
• Experimental Realization of Quantum Artificial Intelligence
• Provably efficient machine learning for quantum many-body problems
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Training Quantum Embedding Kernels on Near-Term Quantum Computers
• Capacity and quantum geometry of parametrized quantum circuits
• Fisher Information in Noisy Intermediate-Scale Quantum Applications
• Recent advances for quantum classifiers
• Application of Quantum Machine Learning using the Quantum Kernel Algorithm on High Energy Physics Analysis at the LHC
• Classical surrogates for quantum learning models
• Importance sampling of randomized measurements for probing entanglement
• Noisy intermediate-scale quantum algorithm for semidefinite programming
• Optimal training of variational quantum algorithms without barren plateaus
• Natural parameterized quantum circuit
• Experimental SWAP test of infinite dimensional quantum states

Cited by in corpus (20)

• Quantum machine learning beyond kernel methods
• Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines
• Shadows of quantum machine learning
• Quantum Kernel Methods under Scrutiny: A Benchmarking Study
• High Dimensional Quantum Machine Learning With Small Quantum Computers
• Quantum Gaussian Process Regression for Bayesian Optimization
• Demonstration of Robust and Efficient Quantum Property Learning with Shallow Shadows
• Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
• Networked Quantum Services
• Reinforcement learning-based architecture search for quantum machine learning
• Reconstructing charged particle track segments with a quantum-enhanced support vector machine
• Distributed Quantum Neural Networks via Partitioned Features Encoding
• Continuous-variable quantum kernel method on a programmable photonic quantum processor
• Quantum Next-Generation Reservoir Computing and Its Quantum Optical Implementation
• On the similarity of bandwidth-tuned quantum kernels and classical kernels
• Holographic Classical Shadow Tomography
• Predicting fermionic densities using a Projected Quantum Kernel method
• Generating Quantum Reservoir State Representations with Random Matrices
• Quantum fidelity kernel with a trapped-ion simulation platform
• Exploring fixed points and eigenstates of quantum systems with reinforcement learning