Structural risk minimization for quantum linear classifiers

QCAE-QOC-SVM: A hybrid quantum machine learning model for DoS and Fuzzy attack detection on autonomous vehicle CAN bus.

In recent years, parameterized quantum circuits have been regarded as machine learning models within the framework of the hybrid quantum–classical approach. Quantum machine learning (QML) has been applied to binary classification problems and unsupervised learning. However, practical quantum application to nonlinear regression tasks has received considerably less attention. Here, we develop QML models designed for predicting the toxicity of 221 phenols on the basis of quantitative structure activity relationship. The results suggest that our data encoding enhanced by quantum entanglement provided more expressive power than the previous ones, implying that quantum correlation could be beneficial for the feature map representation of classical data. Our QML models performed significantly better than the multiple linear regression method. Furthermore, our simulations indicate that the QML models were comparable to those obtained using radial basis function networks, while improving the generalization performance. The present study implies that QML could be an alternative approach for nonlinear regression tasks such as cheminformatics.

Adversarial noise attacks present a significant threat to quantum machine learning (QML) models, similar to their classical counterparts. This is especially true in the current Noisy Intermediate-Scale Quantum era, where noise is unavoidable. Therefore, it is essential to ensure the robustness of QML models before their deployment. To address this challenge, we introduce VeriQR, the first tool designed specifically for formally verifying and improving the robustness of QML models, to the best of our knowledge. This tool mimics real-world quantum hardware’s noisy impacts by incorporating random noise to formally validate a QML model’s robustness. VeriQR supports exact (sound and complete) algorithms for both local and global robustness verification. For enhanced efficiency, it implements an under-approximate (complete) algorithm and a tensor network-based algorithm to verify local and global robustness, respectively. As a formal verification tool, VeriQR can detect adversarial examples and utilize them for further analysis and to enhance the local robustness through adversarial training, as demonstrated by experiments on real-world quantum machine learning models. Moreover, it permits users to incorporate customized noise. Based on this feature, we assess VeriQR using various real-world examples, and experimental outcomes confirm that the addition of specific quantum noise can enhance the global robustness of QML models. These processes are made accessible through a user-friendly graphical interface provided by VeriQR, catering to general users without requiring a deep understanding of the counter-intuitive probabilistic nature of quantum computing.

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.

The quantum kernel method is one of the key approaches to quantum machine learning, which has the advantage of not requiring optimization and its theoretical simplicity. By virtue of these properties, several experimental demonstrations and discussions of the potential advantages have been developed so far. However, as is the case in classical machine learning, not all quantum machine learning models could be regarded as kernel methods. In this work, we explore a quantum machine learning model with a deep parametrized quantum circuit and aim to go beyond the conventional quantum kernel method. In this case, the expressive power and performance are expected to be enhanced, while the training process might be a bottleneck because of the barren plateaus. Moreover, the high computational cost of gradient-based optimization and the large search space of the gradient-free optimization directly make the training intractable. However, we find that parameters of a deep enough quantum circuit do not move much from their initial values during training, allowing for a first-order expansion with respect to the parameters. This behavior is similar to that of the neural tangent kernel in classical machine learning, and such a quantum machine learning with deep variational quantum circuits can be described by another emergent kernel, the . We show that the proposed quantum tangent kernel has the potential to outperform the conventional quantum kernel method by performing a classification task on an ansatz-generated dataset. This work provides a different direction beyond the conventional quantum kernel method and explores the potential power of quantum machine learning with deep parametrized quantum circuits. Published by the American Physical Society 2024

Quantum machine learning (QML) models use encoding circuits to map data into a quantum Hilbert space. While it is well known that the architecture of these circuits significantly influences core properties of the resulting model, they are often chosen heuristically. In this work, we present a approach using reinforcement learning techniques to generate problem-specific encoding circuits to improve the performance of QML models. By specifically using a model-based reinforcement learning algorithm, we reduce the number of necessary circuit evaluations during the search, providing a sample-efficient framework. In contrast to previous search algorithms, our method uses a layered circuit structure that significantly reduces the search space. Additionally, our approach can account for multiple objectives such as solution quality and circuit depth. We benchmark our tailored circuits against various reference models, including models with problem-agnostic circuits and classical models. Our results highlight the effectiveness of problem-specific encoding circuits in enhancing QML model performance.

The evolution of cyberattacks requires a continuous race to implement increasingly sophisticated techniques that allow us to stay ahead of cybercriminals. Thus, a relevant inverse problem in cybersecurity involves determining underlying patterns or models of possible cyber threats based on observed data. In particular, the processing of massive data combined with the application of Machine Learning methods and other techniques derived from Artificial Intelligence have so far achieved very significant advances in preventing and mitigating the impact of many cyberattacks. Given that the keyword in cybersecurity is anticipation, this work explores the possibilities of quantum computing and, in particular, of Quantum Machine Learning to have, when the quantum computing era arrives, the most optimal parameterisations to put these models into practice. Although the application of quantum technologies in a real context may still seem distant, having studies to assess the future viability of Quantum Machine Learning to identify different types of cyberattacks may be a differential element when it comes to ensuring the cybersecurity of essential services. For this reason, this work aims to use several datasets of known problems in the field of cybersecurity to evaluate the most optimal parameterisations in some known Quantum Machine Learning models, comparing the results with those obtained using classical models. After analysing the results of this study, it can be concluded that Quantum Machine Learning techniques are promising in the context of cybersecurity, giving rise to future work on a wider range of cybersecurity datasets and Quantum Machine Learning algorithms.

Active learning (AL) has been widely applied in chemistry and materials science. In this work, we propose a quantum active learning (QAL) method for automatic structural determination of doped nanoparticles, where quantum machine learning (QML) models for regression are used iteratively to indicate new structures to be calculated by Density Functional Theory (DFT) or Density Functional Based Tight Binding (DFTB) and this new data acquisition is used to retrain the QML models. The QAL method is implemented in the Quantum Machine Learning Software/ Agent for Material Design and Discovery (QMLMaterial), whose aim is using an artificial agent (defined by QML regression algorithms) that chooses the next doped configuration to be calculated that has a higher probability of finding the optimum structure. The QAL uses a quantum Gaussian process with a fidelity quantum kernel as well as the projected quantum kernel and different quantum circuits. For comparison, classical AL was used with classical Gaussian process with different classical kernels. The presented QAL method was applied in the structural determination of doped Si11 with 4 Al (4Al@Si11) and the results indicate the QAL method is able to find the optimum 4Al@Si11 structure. The aim of this work is to present the QAL method, formulated in a noise-free quantum computing framework, for automatic structural determination of doped nanoparticles and materials defects.

Variational quantum algorithms (VQAs) have been successfully applied to quantum approximate optimization algorithms, variational quantum compiling, and quantum machine learning models. The performance of VQAs is significantly influenced by the architecture of parameterized quantum circuits (PQCs). Quantum architecture search aims to automatically discover high-performance quantum circuits for specific VQA tasks. Quantum architecture search algorithms that utilize both SuperCircuit training and a parameter-sharing approach can save computational resources. If we directly follow the parameter-sharing approach, the SuperCircuit has to be trained to compensate for the worse search space. To address the challenges posed by the worse search space, we introduce an optimization strategy known as the efficient continuous evolutionary approach using Non-dominated Sorting Genetic Algorithm-II (NSGA-II). Then, we leverage prior information (symmetric property) designing Structure Symmetric Pruning for removing redundant gates of the searched ansatz. Experiments show that the efficient continuous evolutionary approach can search for more quantum architectures with better performance; the number of high-performance ansatzes obtained by our method is 10% higher than that in the literature (Du et al. in npj Quantum Inf. 8:62, 2022). The application of Structure Symmetric Pruning effectively reduces the number of parameters in quantum circuits without compromising their performance significantly. In binary classification tasks, the pruned quantum circuits exhibit an average accuracy reduction of 0.044 compared to their unpruned counterparts.

Quantum machine learning (QML) is an emerging field combining quantum computing and artificial intelligence, with promising applications in medicine and healthcare. This survey reviews more than 60 studies published between 2018 and 2025, highlighting a sharp increase in research activity, especially in the last three years. We address seven core research questions related to publication trends, the use of real quantum hardware versus simulators, quantum architectures overview, dataset types, medical domains, algorithmic frameworks, and reported results. Our analysis shows that most QML research in healthcare is conducted on simulators due to limited hardware access, and it relies on small datasets. Quantum convolutional neural network (QCNN) architectures dominate image-based medical tasks such as tumor detection, pneumonia diagnosis, and ECG interpretation, while feature-based datasets are mainly analyzed with variational quantum classifiers and quantum support vector machines. Despite hardware constraints, QML models often match or surpass classical machine learning approaches in accuracy, frequently reaching 95–99%. However, these performance statements should be qualified to recognize experimental limitations and avoid excessive optimism and should not be interpreted as definitive proof of quantum superiority at this stage. Additionally, issues with reproducibility and reporting of hardware details persist, which is a significant research gap. This review emphasizes the need for standardized benchmarks, more real hardware testing, and architecture-aware algorithm design. With the potential for accelerated diagnostics and personalized healthcare, QML represents a strategic direction for future medical research.

This study evaluates gate-based quantum machine learning (QML) models, including the Variational Quantum Classifier (VQC) and Quantum k-Nearest Neighbors (QkNN), on the QM9 quantum chemistry dataset for binary classification of molecular electronic properties. Using IBM Qiskit, both models were tested on simulators and real quantum hardware. Classical models (LightGBM, SVM, MLP) served as benchmarks. Results show classical models outperform quantum ones, with LightGBM achieving the highest AUC-ROC (0.901). However, VQC on simulators achieved a competitive AUC of 0.781, and real hardware still yielded performance above that of chance. Despite hardware constraints, quantum models demonstrated learning capability. The findings support hybrid quantum-classical systems as a promising near-term approach while quantum hardware continues to evolve

Image classification, a pivotal task in multiple industries, faces computational challenges due to the burgeoning volume of visual data. This research addresses these challenges by introducing two quantum machine learning models that leverage the principles of quantum mechanics for effective computations. Our first model, a hybrid quantum neural network with parallel quantum circuits, enables the execution of computations even in the noisy intermediate-scale quantum era, where circuits with a large number of qubits are currently infeasible. This model demonstrated a record-breaking classification accuracy of 99.21% on the full MNIST dataset, surpassing the performance of known quantum–classical models, while having eight times fewer parameters than its classical counterpart. Also, the results of testing this hybrid model on a Medical MNIST (classification accuracy over 99%), and on CIFAR-10 (classification accuracy over 82%), can serve as evidence of the generalizability of the model and highlights the efficiency of quantum layers in distinguishing common features of input data. Our second model introduces a hybrid quantum neural network with a Quanvolutional layer, reducing image resolution via a convolution process. The model matches the performance of its classical counterpart, having four times fewer trainable parameters, and outperforms a classical model with equal weight parameters. These models represent advancements in quantum machine learning research and illuminate the path towards more accurate image classification systems.

Quantum machine learning (QML) has emerged as a promising direction in the noisy intermediate-scale quantum (NISQ) era, offering computational and memory advantages by harnessing superposition and entanglement. However, QML models often face challenges in scalability and expressiveness due to hardware constraints. In this paper, we propose quantum mixture of experts (QMoE), a novel quantum architecture that integrates the mixture of experts (MoE) paradigm into the QML setting. QMoE comprises multiple parameterized quantum circuits serving as expert models, along with a learnable quantum routing mechanism that selects and aggregates specialized quantum experts per input. The empirical results from the proposed QMoE on quantum classification tasks demonstrate that it consistently outperforms standard quantum neural networks, highlighting its effectiveness in learning complex data patterns. Our work paves the way for scalable and interpretable quantum learning frameworks.

Quantum computing is proving to be very beneficial for solving complex machine learning problems. Quantum computers are inherently excellent in handling and manipulating vectors and matrix operations. The ever increasing size of data has started creating bottlenecks for classical machine learning systems. Quantum computers are emerging as potential solutions to tackle big data related problems. This paper presents a quantum machine learning model based on quantum support vector machine (QSVM) algorithm to solve a classification problem. The quantum machine learning model is practically implemented on quantum simulators and real-time superconducting quantum processors. The performance of quantum machine learning model is computed in terms of processing speed and accuracy and compared against its classical counterpart. The breast cancer dataset is used for the classification problem. The results are indicative that quantum computers offer quantum speed-up.

Managing parking space in city areas is a big issue that impacts traffic, air cleanliness, and how easy it is for people to find a place to park. In this research, the authors are proposing a new approach to overcome this problem using quantum computing techniques, specifically quantum image processing and quantum machine learning, to detect vacant parking spaces from live video feeds. This new method uses the strong points of quantum algorithms for spotting patterns and objects. The methodology involves pre-processing parking lot video data and employing quantum image processing techniques like quantum wavelet transforms and quantum pattern recognition algorithms to identify vacant spaces. Moreover, the authors look into quantum machine learning models, such as quantum neural networks and quantum support vector machines, to make the detection of open spots more accurate. They test how well these quantum methods work by using a big mix of parking lot cases and comparing them with traditional machine learning methods like convolutional neural networks. The findings show that bringing quantum computing into parking space management systems can work well and has possible upsides, shining a light on where quantum algorithms do better and pointing out what needs more work in future studies. In this project, the authors dived into how quantum computing can be used in seeing things through computers and managing city infrastructure.