Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Quantum Information and Computation

Quantum speedup of training radial basis function networks

Changpeng Shao

Published Jun 1, 2019• 6 citations
Publisher

Abstract

Radial basis function (RBF) network is a simple but useful neural network model that contains wide applications in machine learning. The training of an RBF network reduces to solve a linear system, which is time consuming classically. Based on HHL algorithm, we propose two quantum algorithms to train RBF networks. To apply the HHL algorithm, we choose using the Hamiltonian simulation algorithm proposed in [P. Rebentrost, A. Steffens, I. Marvian and S. Lloyd, Phys. Rev. A 97, 012327, 2018]. However, to use this result, an oracle to query the entries of the matrix of the network should be constructed. We apply the amplitude estimation technique to build this oracle. The final results indicate that if the centers of the RBF network are the training samples, then the quantum computer achieves exponential speedup at the number and the dimension of training samples over the classical computer; if the centers are determined by the K-means algorithm, then the quantum computer achieves quadratic speedup at the number of samples and exponential speedup at the dimension of samples.

DOI
10.26421/qic19.7-8-6

Related papers

Quantum speedup of training radial basis function networks

ShaoChangpeng

Radial basis function (RBF) network is a simple but useful neural network model that contains wide applications in machine learning. The training of an RBF network reduces to solve a linear system,...

Quantum Information and Computation•Jun 1, 2019•1 citation

Data classification by quantum radial-basis-function networks

Changpeng Shao

Radial-basis-function (RBF) networks are third-layered neural networks that are widely used in function approximation and data classification. Here we propose a quantum model for RBF networks. As in the classical case, we use radial basis functions as activation functions; quantum linear algebraic techniques and coherent states can be applied to implement these functions. We define the state of the weight as a tensor product of single-qubit states. This gives a simple approach to implement the quantum RBF network in quantum circuits. In this model we prove that training is almost quadratically faster than in the classical case. We demonstrate numerically that the quantum RBF network can solve binary classification problems as effectively as the classical RBF network, while the time and number of iterations used for training are much smaller.

arXiv:1910.08798•Physical Review A•Oct 30, 2020•16 citations

A simple approach to design quantum neural networks and its applications to kernel-learning methods

Changpeng Shao

We give an explicit simple method to build quantum neural networks (QNNs) to solve classification problems. Besides the input (state preparation) and output (amplitude estimation), it has one hidden layer which uses a tensor product of $\log M$ two-dimensional rotations to introduce $\log M$ weights. Here $M$ is the number of training samples. We also have an efficient method to prepare the quantum states of the training samples. By the quantum-classical hybrid method or the variational method, the training algorithm of this QNN is easy to accomplish in a quantum computer. The idea is inspired by the kernel methods and the radial basis function (RBF) networks. In turn, the construction of QNN provides new findings in the design of RBF networks. As an application, we introduce a quantum-inspired RBF network, in which the number of weight parameters is $\log M$. Numerical tests indicate that the performance of this neural network in solving classification problems improves when $M$ increases. Since using exponentially fewer parameters, more advanced optimization methods (e.g. Newton's method) can be used to train this network. Finally, about the convex optimization problem to train support vector machines, we use a similar idea to reduce the number of variables, which equals $M$, to $\log M$.

•Oct 19, 2019•2 citations

Quantum radial basis function methods for scattered data fitting

Lingxia Cui, Hua Xiang

Scattered data fitting is a frequently encountered problem for reconstructing an unknown function from given scattered data. Radial basis function (RBF) methods have proven to be highly useful to deal with this problem. We describe two quantum algorithms to efficiently fit scattered data based on globally and compactly supported RBFs respectively. For the globally supported RBF method, the core of the quantum algorithm relies on using coherent states to calculate the radial functions and a nonsparse matrix exponentiation technique for efficiently performing a matrix inversion. A quadratic speedup is achieved in the number of data over the classical algorithms. For the compactly supported RBF method, we mainly use the HHL algorithm as a subroutine to design an efficient quantum procedure that runs in time logarithmic in the number of data, achieving an exponential improvement over the classical methods.

arXiv:2112.10179•Dec 19, 2021•0 citations

Quantum radial basis function method for the Poisson equation

Lingxia Cui, Zongmin Wu, Hua Xiang

Abstract The radial basis function (RBF) method is widely used for the numerical solution of the Poisson problem in high dimension, where the approximate solution can be found by solving a large system of linear equations. We demonstrate that the RBF method can be accelerated on a quantum computer by using an efficient quantum algorithm for linear equations. We compare the theoretical performance of our quantum algorithm with that of a standard classical algorithm, and find that the quantum algorithm can achieve a polynomial speedup.

arXiv:2301.06032•Journal of Physics A Mathematical and Theoretical•Apr 19, 2023•5 citations

Classification using quantum kernels in a radial basis function network

Emily Micklethwaite, Adam Lowe

Radial basis function (RBF) networks are expanded to incorporate quantum kernel functions enabling a new type of hybrid quantum-classical machine learning algorithm. Using this approach, synthetic examples are introduced which allow for proof of concept on interpolation and classification applications. Quantum kernels have primarily been applied to support vector machines (SVMs), however the quantum kernel RBF network offers potential benefit over quantum kernel based SVMs due to the RBF networks ability to perform multi-class classification natively compared to the standard implementation of the SVM.

quant-pharXiv:2512.20567•Dec 24, 2025•1 citation
Radial basis function (RBF) network is a simple but useful neural network model that contains wide applications in machine learning. The training of an RBF network reduces to solve a linear system, which is time consuming classically. Based on HHL algorithm, we propose two quantum algorithms to train RBF networks. To apply the HHL algorithm, we choose using the Hamiltonian simulation algorithm proposed in [P. Rebentrost, A. Steffens, I. Marvian and S. Lloyd, Phys. Rev. A 97, 012327, 2018]. However, to use this result, an oracle to query the entries of the matrix of the network should be constructed. We apply the amplitude estimation technique to build this oracle. The final results indicate that if the centers of the RBF network are the training samples, then the quantum computer achieves exponential speedup at the number and the dimension of training samples over the classical computer; if the centers are determined by the K-means algorithm, then the quantum computer achieves quadratic speedup at the number of samples and exponential speedup at the dimension of samples.
Radial-basis-function (RBF) networks are third-layered neural networks that are widely used in function approximation and data classification. Here we propose a quantum model for RBF networks. As in the classical case, we use radial basis functions as activation functions; quantum linear algebraic techniques and coherent states can be applied to implement these functions. We define the state of the weight as a tensor product of single-qubit states. This gives a simple approach to implement the quantum RBF network in quantum circuits. In this model we prove that training is almost quadratically faster than in the classical case. We demonstrate numerically that the quantum RBF network can solve binary classification problems as effectively as the classical RBF network, while the time and number of iterations used for training are much smaller.
We give an explicit simple method to build quantum neural networks (QNNs) to solve classification problems. Besides the input (state preparation) and output (amplitude estimation), it has one hidden layer which uses a tensor product of log⁡M\log MlogM two-dimensional rotations to introduce log⁡M\log MlogM weights. Here MMM is the number of training samples. We also have an efficient method to prepare the quantum states of the training samples. By the quantum-classical hybrid method or the variational method, the training algorithm of this QNN is easy to accomplish in a quantum computer. The idea is inspired by the kernel methods and the radial basis function (RBF) networks. In turn, the construction of QNN provides new findings in the design of RBF networks. As an application, we introduce a quantum-inspired RBF network, in which the number of weight parameters is log⁡M\log MlogM. Numerical tests indicate that the performance of this neural network in solving classification problems improves when MMM increases. Since using exponentially fewer parameters, more advanced optimization methods (e.g. Newton's method) can be used to train this network. Finally, about the convex optimization problem to train support vector machines, we use a similar idea to reduce the number of variables, which equals MMM, to log⁡M\log MlogM.
Scattered data fitting is a frequently encountered problem for reconstructing an unknown function from given scattered data. Radial basis function (RBF) methods have proven to be highly useful to deal with this problem. We describe two quantum algorithms to efficiently fit scattered data based on globally and compactly supported RBFs respectively. For the globally supported RBF method, the core of the quantum algorithm relies on using coherent states to calculate the radial functions and a nonsparse matrix exponentiation technique for efficiently performing a matrix inversion. A quadratic speedup is achieved in the number of data over the classical algorithms. For the compactly supported RBF method, we mainly use the HHL algorithm as a subroutine to design an efficient quantum procedure that runs in time logarithmic in the number of data, achieving an exponential improvement over the classical methods.
Abstract The radial basis function (RBF) method is widely used for the numerical solution of the Poisson problem in high dimension, where the approximate solution can be found by solving a large system of linear equations. We demonstrate that the RBF method can be accelerated on a quantum computer by using an efficient quantum algorithm for linear equations. We compare the theoretical performance of our quantum algorithm with that of a standard classical algorithm, and find that the quantum algorithm can achieve a polynomial speedup.
Radial basis function (RBF) networks are expanded to incorporate quantum kernel functions enabling a new type of hybrid quantum-classical machine learning algorithm. Using this approach, synthetic examples are introduced which allow for proof of concept on interpolation and classification applications. Quantum kernels have primarily been applied to support vector machines (SVMs), however the quantum kernel RBF network offers potential benefit over quantum kernel based SVMs due to the RBF networks ability to perform multi-class classification natively compared to the standard implementation of the SVM.