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

arXiv:2305.11040

Simulation of a Variational Quantum Perceptron using Grover's Algorithm

Nouhaila Innan, Mohamed Bennai

Published May 18, 2023• 0 citations
arXivHTMLPDF

Abstract

The quantum perceptron, the variational circuit, and the Grover algorithm have been proposed as promising components for quantum machine learning. This paper presents a new quantum perceptron that combines the quantum variational circuit and the Grover algorithm. However, this does not guarantee that this quantum variational perceptron with Grover's algorithm (QVPG) will have any advantage over its quantum variational (QVP) and classical counterparts. Here, we examine the performance of QVP and QVP-G by computing their loss function and analyzing their accuracy on the classification task, then comparing these two quantum models to the classical perceptron (CP). The results show that our two quantum models are more efficient than CP, and our novel suggested model QVP-G outperforms the QVP, demonstrating that the Grover can be applied to the classification task and even makes the model more accurate, besides the unstructured search problems.

DOI
10.48550/arxiv.2305.11040

Related papers

A variational quantum perceptron with Grover’s algorithm for efficient classification

Nouhaila Innan, Mohamed Bennai

Abstract This study introduces the Quantum Variational Perceptron with Grover’s algorithm (QVP-G), an innovative Quantum machine Learning (QML) model significantly enhancing binary classification tasks’ capabilities. The study goes beyond theoretical constructs, employing empirical evaluations of QVP-G on the well-established Iris and more complex breast cancer datasets. This dual-dataset approach highlights the model’s adaptability and effectiveness in varied contexts. Our experimental findings reveal the exceptional accuracy of QVP-G, achieving a remarkable 99% success rate. This superior performance is owed mainly to integrating Grover’s algorithm, a cornerstone in Quantum Computing (QC), which substantially increases the probability of accurately determining the correct classification hyperplane. Beyond academic interest, our research positions QVP-G as a powerful tool with substantial practical applications. Its utility ranges from enhancing fraud detection and improving spam filtering to expediting drug discovery and contributing to advances in physics research. This study marks a significant advancement in QML, reinforcing the bridge between QC and machine learning.

Physica Scripta•Apr 12, 2024•14 citations

Quantum Perceptron Revisited: Computational-Statistical Tradeoffs

Mathieu Roget, Giuseppe Di Molfetta, Hachem Kadri

Quantum machine learning algorithms could provide significant speed-ups over their classical counterparts; however, whether they could also achieve good generalization remains unclear. Recently, two quantum perceptron models which give a quadratic improvement over the classical perceptron algorithm using Grover's search have been proposed by Wiebe et al. arXiv:1602.04799 . While the first model reduces the complexity with respect to the size of the training set, the second one improves the bound on the number of mistakes made by the perceptron. In this paper, we introduce a hybrid quantum-classical perceptron algorithm with lower complexity and better generalization ability than the classical perceptron. We show a quadratic improvement over the classical perceptron in both the number of samples and the margin of the data. We derive a bound on the expected error of the hypothesis returned by our algorithm, which compares favorably to the one obtained with the classical online perceptron. We use numerical experiments to illustrate the trade-off between computational complexity and statistical accuracy in quantum perceptron learning and discuss some of the key practical issues surrounding the implementation of quantum perceptron models into near-term quantum devices, whose practical implementation represents a serious challenge due to inherent noise. However, the potential benefits make correcting this worthwhile.

•Jan 1, 2022•0 citations

Quantum Perceptron Revisited: Computational-Statistical Tradeoffs

Mathieu Roget, Giuseppe Di Molfetta, Hachem Kadri

Quantum machine learning algorithms could provide significant speed-ups over their classical counterparts; however, whether they could also achieve good generalization remains unclear. Recently, two quantum perceptron models which give a quadratic improvement over the classical perceptron algorithm using Grover's search have been proposed by Wiebe et al. arXiv:1602.04799 . While the first model reduces the complexity with respect to the size of the training set, the second one improves the bound on the number of mistakes made by the perceptron. In this paper, we introduce a hybrid quantum-classical perceptron algorithm with lower complexity and better generalization ability than the classical perceptron. We show a quadratic improvement over the classical perceptron in both the number of samples and the margin of the data. We derive a bound on the expected error of the hypothesis returned by our algorithm, which compares favorably to the one obtained with the classical online perceptron. We use numerical experiments to illustrate the trade-off between computational complexity and statistical accuracy in quantum perceptron learning and discuss some of the key practical issues surrounding the implementation of quantum perceptron models into near-term quantum devices, whose practical implementation represents a serious challenge due to inherent noise. However, the potential benefits make correcting this worthwhile.

arXiv:2106.02496•Jun 4, 2021•1 citation

Implementable Quantum Classifier for Nonlinear Data

Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu +1 more

In this Letter, we propose a quantum machine learning scheme for the classification of classical nonlinear data. The main ingredients of our method are variational quantum perceptron (VQP) and a quantum generalization of classical ensemble learning. Our VQP employs parameterized quantum circuits to learn a Grover search (or amplitude amplification) operation with classical optimization, and can achieve quadratic speedup in query complexity compared to its classical counterparts. We show how the trained VQP can be used to predict future data with $O(1)$ {query} complexity. Ultimately, a stronger nonlinear classifier can be established, the so-called quantum ensemble learning (QEL), by combining a set of weak VQPs produced using a subsampling method. The subsampling method has two significant advantages. First, all $T$ weak VQPs employed in QEL can be trained in parallel, therefore, the query complexity of QEL is equal to that of each weak VQP multiplied by $T$. Second, it dramatically reduce the {runtime} complexity of encoding circuits that map classical data to a quantum state because this dataset can be significantly smaller than the original dataset given to QEL. This arguably provides a most satisfactory solution to one of the most criticized issues in quantum machine learning proposals. To conclude, we perform two numerical experiments for our VQP and QEL, implemented by Python and pyQuil library. Our experiments show that excellent performance can be achieved using a very small quantum circuit size that is implementable under current quantum hardware development. Specifically, given a nonlinear synthetic dataset with $4$ features for each example, the trained QEL can classify the test examples that are sampled away from the decision boundaries using $146$ single and two qubits quantum gates with $92\%$ accuracy.

•Sep 17, 2018•10 citations

Variational quantum algorithms for machine learning: theory and applications

Stefano Mangini

This Ph.D. thesis provides a comprehensive review of the state-of-the-art in the field of Variational Quantum Algorithms and Quantum Machine Learning, including numerous original contributions. The first chapters are devoted to a brief summary of quantum computing and an in-depth analysis of variational quantum algorithms. The discussion then shifts to quantum machine learning, where an introduction to the elements of machine learning and statistical learning theory is followed by a review of the most common quantum counterparts of machine learning models. Next, several novel contributions to the field based on previous work are presented, namely: a newly introduced model for a quantum perceptron with applications to recognition and classification tasks; a variational generalization of such a model to reduce the circuit footprint of the proposed architecture; an industrial use case of a quantum autoencoder followed by a quantum classifier used to analyze classical data from an industrial power plant; a study of the entanglement features of quantum neural network circuits; and finally, a noise deconvolution technique to remove a large class of noise when performing arbitrary measurements on qubit systems.

arXiv:2306.09984•Jun 16, 2023•4 citations

Variational Learning of Grover’s Search Algorithm with Partial Diffusion Operator

P. Ostovar, N. Majd

This paper introduces a new approach to improve Grover's search algorithm by utilizing variational learning, with a specific focus on incorporating a partial diffusion operator. Grover's search algorithm is a well-known quantum algorithm that provides a quadratic speedup for searching an unsorted database. However, its performance can be further enhanced by modifying its diffusion operator. In this work, we aim to identify a parameterized quantum circuit that can effectively learn and optimize Grover's search algorithm, incorporating a partial diffusion operator. The key idea behind this approach is to use variational learning, a technique that employs parameterized quantum circuits to optimize the algorithm's performance. By adjusting the parameters of the quantum circuit, the algorithm can be tailored to better solve the search problem. Variational learning is employed to determine the optimal parameters for the partial diffusion operator, enabling the quantum circuit to adapt to different problem instances. Our experimental results demonstrate that the optimized quantum circuit outperforms the traditional Grover’s algorithm that uses the standard partial diffusion operator. The results suggest that the proposed approach offers significant improvements in terms of algorithmic efficiency and performance. This advancement could have important implications for the development of quantum algorithms, particularly in applications related to database search and optimization problems. In conclusion, this paper presents a promising new method to enhance Grover's search algorithm, utilizing variational learning and a partial diffusion operator, with results showing improved performance over the original algorithm.

Transactions on Machine Intelligence•Nov 25, 2018•0 citations
The quantum perceptron, the variational circuit, and the Grover algorithm have been proposed as promising components for quantum machine learning. This paper presents a new quantum perceptron that combines the quantum variational circuit and the Grover algorithm. However, this does not guarantee that this quantum variational perceptron with Grover's algorithm (QVPG) will have any advantage over its quantum variational (QVP) and classical counterparts. Here, we examine the performance of QVP and QVP-G by computing their loss function and analyzing their accuracy on the classification task, then comparing these two quantum models to the classical perceptron (CP). The results show that our two quantum models are more efficient than CP, and our novel suggested model QVP-G outperforms the QVP, demonstrating that the Grover can be applied to the classification task and even makes the model more accurate, besides the unstructured search problems.
Abstract This study introduces the Quantum Variational Perceptron with Grover’s algorithm (QVP-G), an innovative Quantum machine Learning (QML) model significantly enhancing binary classification tasks’ capabilities. The study goes beyond theoretical constructs, employing empirical evaluations of QVP-G on the well-established Iris and more complex breast cancer datasets. This dual-dataset approach highlights the model’s adaptability and effectiveness in varied contexts. Our experimental findings reveal the exceptional accuracy of QVP-G, achieving a remarkable 99% success rate. This superior performance is owed mainly to integrating Grover’s algorithm, a cornerstone in Quantum Computing (QC), which substantially increases the probability of accurately determining the correct classification hyperplane. Beyond academic interest, our research positions QVP-G as a powerful tool with substantial practical applications. Its utility ranges from enhancing fraud detection and improving spam filtering to expediting drug discovery and contributing to advances in physics research. This study marks a significant advancement in QML, reinforcing the bridge between QC and machine learning.
Quantum machine learning algorithms could provide significant speed-ups over their classical counterparts; however, whether they could also achieve good generalization remains unclear. Recently, two quantum perceptron models which give a quadratic improvement over the classical perceptron algorithm using Grover's search have been proposed by Wiebe et al. arXiv:1602.04799 . While the first model reduces the complexity with respect to the size of the training set, the second one improves the bound on the number of mistakes made by the perceptron. In this paper, we introduce a hybrid quantum-classical perceptron algorithm with lower complexity and better generalization ability than the classical perceptron. We show a quadratic improvement over the classical perceptron in both the number of samples and the margin of the data. We derive a bound on the expected error of the hypothesis returned by our algorithm, which compares favorably to the one obtained with the classical online perceptron. We use numerical experiments to illustrate the trade-off between computational complexity and statistical accuracy in quantum perceptron learning and discuss some of the key practical issues surrounding the implementation of quantum perceptron models into near-term quantum devices, whose practical implementation represents a serious challenge due to inherent noise. However, the potential benefits make correcting this worthwhile.
Quantum machine learning algorithms could provide significant speed-ups over their classical counterparts; however, whether they could also achieve good generalization remains unclear. Recently, two quantum perceptron models which give a quadratic improvement over the classical perceptron algorithm using Grover's search have been proposed by Wiebe et al. arXiv:1602.04799 . While the first model reduces the complexity with respect to the size of the training set, the second one improves the bound on the number of mistakes made by the perceptron. In this paper, we introduce a hybrid quantum-classical perceptron algorithm with lower complexity and better generalization ability than the classical perceptron. We show a quadratic improvement over the classical perceptron in both the number of samples and the margin of the data. We derive a bound on the expected error of the hypothesis returned by our algorithm, which compares favorably to the one obtained with the classical online perceptron. We use numerical experiments to illustrate the trade-off between computational complexity and statistical accuracy in quantum perceptron learning and discuss some of the key practical issues surrounding the implementation of quantum perceptron models into near-term quantum devices, whose practical implementation represents a serious challenge due to inherent noise. However, the potential benefits make correcting this worthwhile.
In this Letter, we propose a quantum machine learning scheme for the classification of classical nonlinear data. The main ingredients of our method are variational quantum perceptron (VQP) and a quantum generalization of classical ensemble learning. Our VQP employs parameterized quantum circuits to learn a Grover search (or amplitude amplification) operation with classical optimization, and can achieve quadratic speedup in query complexity compared to its classical counterparts. We show how the trained VQP can be used to predict future data with O(1)O(1)O(1) {query} complexity. Ultimately, a stronger nonlinear classifier can be established, the so-called quantum ensemble learning (QEL), by combining a set of weak VQPs produced using a subsampling method. The subsampling method has two significant advantages. First, all TTT weak VQPs employed in QEL can be trained in parallel, therefore, the query complexity of QEL is equal to that of each weak VQP multiplied by TTT. Second, it dramatically reduce the {runtime} complexity of encoding circuits that map classical data to a quantum state because this dataset can be significantly smaller than the original dataset given to QEL. This arguably provides a most satisfactory solution to one of the most criticized issues in quantum machine learning proposals. To conclude, we perform two numerical experiments for our VQP and QEL, implemented by Python and pyQuil library. Our experiments show that excellent performance can be achieved using a very small quantum circuit size that is implementable under current quantum hardware development. Specifically, given a nonlinear synthetic dataset with 444 features for each example, the trained QEL can classify the test examples that are sampled away from the decision boundaries using 146146146 single and two qubits quantum gates with 92%92\%92% accuracy.
This Ph.D. thesis provides a comprehensive review of the state-of-the-art in the field of Variational Quantum Algorithms and Quantum Machine Learning, including numerous original contributions. The first chapters are devoted to a brief summary of quantum computing and an in-depth analysis of variational quantum algorithms. The discussion then shifts to quantum machine learning, where an introduction to the elements of machine learning and statistical learning theory is followed by a review of the most common quantum counterparts of machine learning models. Next, several novel contributions to the field based on previous work are presented, namely: a newly introduced model for a quantum perceptron with applications to recognition and classification tasks; a variational generalization of such a model to reduce the circuit footprint of the proposed architecture; an industrial use case of a quantum autoencoder followed by a quantum classifier used to analyze classical data from an industrial power plant; a study of the entanglement features of quantum neural network circuits; and finally, a noise deconvolution technique to remove a large class of noise when performing arbitrary measurements on qubit systems.
This paper introduces a new approach to improve Grover's search algorithm by utilizing variational learning, with a specific focus on incorporating a partial diffusion operator. Grover's search algorithm is a well-known quantum algorithm that provides a quadratic speedup for searching an unsorted database. However, its performance can be further enhanced by modifying its diffusion operator. In this work, we aim to identify a parameterized quantum circuit that can effectively learn and optimize Grover's search algorithm, incorporating a partial diffusion operator. The key idea behind this approach is to use variational learning, a technique that employs parameterized quantum circuits to optimize the algorithm's performance. By adjusting the parameters of the quantum circuit, the algorithm can be tailored to better solve the search problem. Variational learning is employed to determine the optimal parameters for the partial diffusion operator, enabling the quantum circuit to adapt to different problem instances. Our experimental results demonstrate that the optimized quantum circuit outperforms the traditional Grover’s algorithm that uses the standard partial diffusion operator. The results suggest that the proposed approach offers significant improvements in terms of algorithmic efficiency and performance. This advancement could have important implications for the development of quantum algorithms, particularly in applications related to database search and optimization problems. In conclusion, this paper presents a promising new method to enhance Grover's search algorithm, utilizing variational learning and a partial diffusion operator, with results showing improved performance over the original algorithm.