Abstract As restricted quantum computers become available, research focuses on finding meaningful applications. For example, in quantum machine learning, a special type of quantum circuit called a quantum neural network is one of the most investigated approaches. However, we know little about suitable circuit architectures or important model hyperparameters for a given task. In this work, we apply the functional ANOVA framework to the quantum neural network architectures to analyze which of the quantum machine learning hyperparameters are most influential for their predictive performance. We restrict our study to 7 open-source datasets from the OpenML-CC18 classification benchmark, which are small enough for simulations on quantum hardware with fewer than 20 qubits. Using this framework, three main levels of importance were identified, confirming expected patterns and revealing new insights. For instance, the learning rate is identified as the most important hyperparameter on all datasets, whereas the particular choice of entangling gates used is found to be the least important on all except for one dataset. In addition to identifying the relevant hyperparameters, for each of them, we also learned data-driven priors based on values that perform well on previously seen datasets, which can then be used to steer hyperparameter optimization processes. We utilize these priors in the hyperparameter optimization method hyperband and show that these improve performance against uniform sampling across all datasets by, on average, $0.53 \%$ 0.53 % , up to $6.11 \%$ 6.11 % , in cross-validation accuracy. We also demonstrate that such improvements hold on average regardless of the configuration hyperband is run with. Our work introduces new methodologies for studying quantum machine learning models toward quantum model selection in practice. All research code is made publicly available.Abstract As restricted quantum computers become available, research focuses on finding meaningful applications. For example, in quantum machine learning, a special type of quantum circuit called a quantum neural network is one of the most investigated approaches. However, we know little about suitable circuit architectures or important model hyperparameters for a given task. In this work, we apply the functional ANOVA framework to the quantum neural network architectures to analyze which of the quantum machine learning hyperparameters are most influential for their predictive performance. We restrict our study to 7 open-source datasets from the OpenML-CC18 classification benchmark, which are small enough for simulations on quantum hardware with fewer than 20 qubits. Using this framework, three main levels of importance were identified, confirming expected patterns and revealing new insights. For instance, the learning rate is identified as the most important hyperparameter on all datasets, whereas the particular choice of entangling gates used is found to be the least important on all except for one dataset. In addition to identifying the relevant hyperparameters, for each of them, we also learned data-driven priors based on values that perform well on previously seen datasets, which can then be used to steer hyperparameter optimization processes. We utilize these priors in the hyperparameter optimization method hyperband and show that these improve performance against uniform sampling across all datasets by, on average, $$0.53 \%$$ 0.53 % , up to $$6.11 \%$$ 6.11 % , in cross-validation accuracy. We also demonstrate that such improvements hold on average regardless of the configuration hyperband is run with. Our work introduces new methodologies for studying quantum machine learning models toward quantum model selection in practice. All research code is made publicly available.

Machine LearningAug 31, 202325 citations

Modeling Deep Unfolded Quantum Machine Learning Framework

Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel

Quantum machine learning models, like Quantum Neural Networks (QNN) and Quantum Support Vector Classifiers (QSVC), often struggle with overfitting, slow convergence, and suboptimal generalization across various datasets. This paper explores the advantages of integrating deep unfolding techniques into quantum models and develops a framework focusing on Deep Unfolded Variational Quantum Classifiers (DVQC), Deep Unfolded Quantum Neural Networks (DQNN), and Deep Unfolded QSVC (DQSVC). Our novel unfolding transforms quantum circuit training into a sequence of learnable layers, with each layer representing an optimization step that concurrently renews both circuit parameters and QNN hyperparameters. The proposed framework significantly improves training and test accuracy by dynamically adjusting learning rate, perturbations and other similar hyperparameters, particularly on complex datasets like Genomic and Breast Cancer. Our evaluation and experiment show that proposed DVQC and DQNN outperform baseline VQC and QNN, achieving 90% training accuracy and up to 20% higher test accuracy on Genomic and Adhoc datasets. DQSVC achieves 100% accuracy on Adhoc and 97% on Genomic datasets, surpassing the 90% test accuracy of traditional QSVC. Our implementation details will be publicly available.Quantum machine learning models, like Quantum Neural Networks (QNN) and Quantum Support Vector Classifiers (QSVC), often struggle with overfitting, slow convergence, and suboptimal generalization across various datasets. This paper explores the advantages of integrating deep unfolding techniques into quantum models and develops a framework focusing on Deep Unfolded Variational Quantum Classifiers (DVQC), Deep Unfolded Quantum Neural Networks (DQNN), and Deep Unfolded QSVC (DQSVC). Our novel unfolding transforms quantum circuit training into a sequence of learnable layers, with each layer representing an optimization step that concurrently renews both circuit parameters and QNN hyperparameters. The proposed framework significantly improves training and test accuracy by dynamically adjusting learning rate, perturbations and other similar hyperparameters, particularly on complex datasets like Genomic and Breast Cancer. Our evaluation and experiment show that proposed DVQC and DQNN outperform baseline VQC and QNN, achieving 90% training accuracy and up to 20% higher test accuracy on Genomic and Adhoc datasets. DQSVC achieves 100% accuracy on Adhoc and 97% on Genomic datasets, surpassing the 90% test accuracy of traditional QSVC. Our implementation details will be publicly available.

IEEE Transactions on Artificial IntelligenceMay 26, 20252 citations

Quantum Neural Networks: Exploring Quantum Enhancements in Deep Learning

Dukuru Chiranjevi, Anisha Mishra, Ranjan Kumar Behera +1 more

Intelligent systems reference libraryJan 1, 20254 citations

Quantum Machine Learning Performance Analysis: Performance Comparison Between Classical Neural Networks and Quantum Neural Networks

Pannatat Manmanee, Chinnapong Angsuchotmetee

This study presents a performance analysis of Quantum Neural Networks (QNN) versus classical benchmarks. We compare three architectures: Classical Artificial Neural Networks (ANN), Variational QNNs (VQNN), and Post-Variational QNNs (Post-QNN) across standard classification datasets (PIMA Diabetes, Heart Disease, and Iris). While VQNNs are theoretically powerful, our experiments reveal significant challenges in hyperparameter tuning and stability, often resulting in suboptimal accuracy. Conversely, the Post-QNN approach—which leverages fixed quantum feature maps and classical optimization—demonstrates superior stability. Our results show that Post-QNNs not only outperform VQNNs by wide margins (e.g., +20% accuracy on Heart Disease) but also match or exceed classical ANN performance. This research highlights the efficacy of Post-Variational methods in overcoming the trainability barriers of standard parameterized quantum circuits.This study presents a performance analysis of Quantum Neural Networks (QNN) versus classical benchmarks. We compare three architectures: Classical Artificial Neural Networks (ANN), Variational QNNs (VQNN), and Post-Variational QNNs (Post-QNN) across standard classification datasets (PIMA Diabetes, Heart Disease, and Iris). While VQNNs are theoretically powerful, our experiments reveal significant challenges in hyperparameter tuning and stability, often resulting in suboptimal accuracy. Conversely, the Post-QNN approach—which leverages fixed quantum feature maps and classical optimization—demonstrates superior stability. Our results show that Post-QNNs not only outperform VQNNs by wide margins (e.g., +20% accuracy on Heart Disease) but also match or exceed classical ANN performance. This research highlights the efficacy of Post-Variational methods in overcoming the trainability barriers of standard parameterized quantum circuits.

International Conference on Informatics, Environment, Energy and Applications (IEEA)Feb 6, 20260 citations

Theory of overparametrization in quantum neural networks

Martín Larocca, Nathan Ju, Diego García-Martín +2 more

arXiv:2109.11676Nature Computational ScienceJun 26, 2023177 citations

0.53 \%

0.53 % , up to

6.11 \%

6.11 % , in cross-validation accuracy. We also demonstrate that such improvements hold on average regardless of the configuration hyperband is run with. Our work introduces new methodologies for studying quantum machine learning models toward quantum model selection in practice. All research code is made publicly available.