Quantum Gaussian Process Regression for Bayesian Optimization

Abstract

Gaussian process regression is a well-established Bayesian machine learning method. We propose a new approach to Gaussian process regression using quantum kernels based on parameterized quantum circuits. By employing a hardware-efficient feature map and careful regularization of the Gram matrix, we demonstrate that the variance information of the resulting quantum Gaussian process can be preserved. We also show that quantum Gaussian processes can be used as a surrogate model for Bayesian optimization, a task that critically relies on the variance of the surrogate model. To demonstrate the performance of this quantum Bayesian optimization algorithm, we apply it to the hyperparameter optimization of a machine learning model which performs regression on a real-world dataset. We benchmark the quantum Bayesian optimization against its classical counterpart and show that quantum version can match its performance.

References in corpus (31)

• XGBoost: A Scalable Tree Boosting System
• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Trapped-Ion Quantum Computing: Progress and Challenges
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• Quantum machine learning beyond kernel methods
• Solving nonlinear differential equations with differentiable quantum circuits
• Supervised quantum machine learning models are kernel methods
• Gaussian Process Regression for Geometry Optimization
• Dynamical decoupling for superconducting qubits: a performance survey
• Quantum advantage with noisy shallow circuits in 3D
• Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learning
• Quantum assisted Gaussian process regression
• Gaussian Process Regression for Transition State Search
• Towards understanding the power of quantum kernels in the NISQ era
• Quantum machine learning of large datasets using randomized measurements
• An analytic comparison of regularization methods for Gaussian Processes
• Quantum Gaussian process regression
• Faster variational quantum algorithms with quantum kernel-based surrogate models
• Exponential concentration in quantum kernel methods
• Benchmarking Automated Machine Learning Methods for Price Forecasting Applications

Cited by in corpus (3)

• Reduction of finite sampling noise in quantum neural networks
• Opportunities and challenges of quantum computing for climate modelling
• Benchmarking of quantum fidelity kernels for Gaussian process regression