arXiv subjects

Filippo Caruso

Publications and source records attributed to Filippo Caruso.

At least 19 recordsLinked to original sources

arXiv2026

Hybrid quantum-classical neural network for sentiment analysis

Quantum machine learning has recently emerged as a promising paradigm that leverages the expressive power of quantum circuits to address complex learning tasks. In this work, we investigate the applicability of hybrid quantum-classical neural networks to sentiment analysis, a central problem in natural language processing. We focus on a dataset of tweets related to COVID-19, where the textual content is vectorized using TF-IDF and fed into both classical feedforward networks and hybrid architectures incorporating parameterized quantum circuits. Our results show that hybrid models can achieve accuracy comparable to the classical baseline, while exhibiting distinct learning dynamics, especially in terms of validation loss and accuracy, that suggest a richer representational capacity. Moreover, when applying transfer learning to an SMS spam classification task, the hybrid models consistently outperform the classical counterpart, achieving an accuracy increase of 15 percentage points (from 66% to 81%) on the spam class, demonstrating enhanced generalization. These findings highlight the feasibility of employing QML for natural language processing and point toward the potential advantages of hybrid models as quantum hardware continues to advance.

cs.LG↗

arXiv2026

Quantum Generative Diffusion Model for Real-World Time Series

Generative models have achieved remarkable success in data synthesis, though recent advances driven by increasing model scale have introduced challenges in computational cost and efficiency. Quantum machine learning offers a promising alternative, representing complex data distributions using compact, highly expressive models. Here, we propose QDiffusion-TS, the first quantum generative diffusion model for time series synthesis, and validate it on the IQM quantum processor. The framework extends a classical diffusion architecture by replacing feed-forward components within the denoising transformer with quantum neural networks, yielding a hybrid quantum transformer that reduces the number of trainable parameters in each replaced component by nearly three orders of magnitude. Evaluated on financial time series from Apple and Amazon, the model generates synthetic data that more accurately reproduces the real distributions, reducing Wasserstein distance by approximately 44% relative to its classical counterpart across both datasets. In a downstream forecasting task, augmentation with the generated data improves predictive performance by up to 71% in RMSE over a baseline trained solely on real data. These results show that quantum enhanced architectures can consistently match and frequently surpass classical performance with substantially fewer parameters, establishing a practical framework towards more efficient and scalable data-driven generative modelling.

cs.LG↗

arXiv2025

Hamiltonian Expressibility for Ansatz Selection in Variational Quantum Algorithms

In the context of Variational Quantum Algorithms (VQAs), selecting an appropriate ansatz is crucial for efficient problem-solving. Hamiltonian expressibility has been introduced as a metric to quantify a circuit's ability to uniformly explore the energy landscape associated with a Hamiltonian ground state search problem. However, its influence on solution quality remains largely unexplored. In this work, we estimate the Hamiltonian expressibility of a well-defined set of circuits applied to various Hamiltonians using a Monte Carlo-based approach. We analyze how ansatz depth influences expressibility and identify the most and least expressive circuits across different problem types. We then train each ansatz using the Variational Quantum Eigensolver (VQE) and analyze the correlation between solution quality and expressibility.Our results indicate that, under ideal or low-noise conditions and particularly for small-scale problems, ans\"atze with high Hamiltonian expressibility yield better performance for problems with non-diagonal Hamiltonians and superposition-state solutions. Conversely, circuits with low expressibility are more effective for problems whose solutions are basis states, including those defined by diagonal Hamiltonians. Under noisy conditions, low-expressibility circuits remain preferable for basis-state problems, while intermediate expressibility yields better results for some problems involving superposition-state solutions.

quant-ph↗

arXiv2025

Analysis of Quantum Image Representations for Supervised Classification

In the era of big data and artificial intelligence, the increasing volume of data and the demand to solve more and more complex computational challenges are two driving forces for improving the efficiency of data storage, processing and analysis. Quantum image processing (QIP) is an interdisciplinary field between quantum information science and image processing, which has the potential to alleviate some of these challenges by leveraging the power of quantum computing. In this work, we compare and examine the compression properties of four different Quantum Image Representations (QImRs): namely, Tensor Network Representation (TNR), Flexible Representation of Quantum Image (FRQI), Novel Enhanced Quantum Representation NEQR, and Quantum Probability Image Encoding (QPIE). Our simulations show that FRQI and QPIE perform a higher compression of image information than TNR and NEQR. Furthermore, we investigate the trade-off between accuracy and memory in binary classification problems, evaluating the performance of quantum kernels based on QImRs compared to the classical linear kernel. Our results indicate that quantum kernels provide comparable classification average accuracy but require exponentially fewer resources for image storage.

quant-ph↗

arXiv2025

Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion

Quantum Diffusion Models (QDMs) are an emerging paradigm in Generative AI that aims to use quantum properties to improve the performances of their classical counterparts. However, existing algorithms are not easily scalable due to the limitations of near-term quantum devices. Following our previous work on QDMs, here we propose and implement two physics-inspired protocols. In the first, we use the formalism of quantum stochastic walks, showing that a specific interplay of quantum and classical dynamics in the forward process produces statistically more robust models generating sets of MNIST images with lower Fr\'echet Inception Distance (FID) than using totally classical dynamics. In the second approach, we realize an algorithm to generate images by exploiting the intrinsic noise of real IBM quantum hardware with only four qubits. Our work could be a starting point to pave the way for new scenarios for large-scale algorithms in quantum Generative AI, where quantum noise is neither mitigated nor corrected, but instead exploited as a useful resource.

quant-ph↗

arXiv2025

Privacy-preserving neutral atom-based quantum classifier towards real healthcare applications

Technological advances in Artificial Intelligence (AI) and Machine Learning (ML) for the healthcare domain are rapidly arising, with a growing discussion regarding the ethical management of their development. In general, ML healthcare applications crucially require performance, interpretability of data, and respect for data privacy. The latter is an increasingly debated topic as commercial cloud computing services become more and more widespread. Recently, dedicated methods are starting to be developed aiming to protect data privacy. However, these generally result in a trade-off forcing one to balance the level of data privacy and the algorithm performance. Here, a Support Vector Machine (SVM) classifier model is proposed whose training is reformulated into a Quadratic Unconstrained Binary Optimization (QUBO) problem, and adapted to a neutral atom-based Quantum Processing Unit (QPU). Our final model does not require anonymization techniques to protect data privacy since the sensitive data are not needed to be transferred to the cloud-available QPU. Indeed, the latter is used only during the training phase, hence allowing a future concrete application in a real-world scenario. Finally, performance and scaling analyses on a publicly available breast cancer dataset are discussed, both using ideal and noisy simulations for the training process, and also successfully tested on a currently available real neutral-atom QPU.

quant-ph↗

arXiv2024

Investigating layer-selective transfer learning of QAOA parameters for Max-Cut problem

The quantum approximate optimization algorithm (QAOA) is a variational quantum algorithm (VQA) ideal for noisy intermediate-scale quantum (NISQ) processors, and is highly successful in solving combinatorial optimization problems (COPs). It has been observed that the optimal parameters obtained from one instance of a COP can be transferred to another instance, resulting in generally good solutions for the latter. In this work, we propose a refinement scheme in which only a subset of QAOA layers is optimized following parameter transfer, with a focus on the Max-Cut problem. Our motivation is to reduce the complexity of the loss landscape when optimizing all the layers of high-depth QAOA circuits, as well as to reduce the optimization time. We investigate the potential hierarchical roles of different layers and analyze how the approximation ratio scales with increasing problem size. Our findings indicate that the selective layer optimization scheme offers a favorable trade-off between solution quality and computational time, and can be more beneficial than full optimization at a lower optimization time.

quant-ph↗

arXiv2024

Machine-learning based high-bandwidth magnetic sensing

Recent years have seen significant growth of quantum technologies, and specifically quantum sensing, both in terms of the capabilities of advanced platforms and their applications. One of the leading platforms in this context is nitrogen-vacancy (NV) color centers in diamond, providing versatile, high-sensitivity, and high-spatial-resolution magnetic sensing. Nevertheless, current schemes for spin resonance magnetic sensing (as applied by NV quantum sensing) suffer from tradeoffs associated with sensitivity, dynamic range, and bandwidth. Here we address this issue, and implement machine learning tools to enhance NV magnetic sensing in terms of the sensitivity/bandwidth tradeoff in large dynamic range scenarios. Our results indicate a potential reduction of required data points by at least a factor of 3, while maintaining the current error level. Our results promote quantum machine learning protocols for sensing applications towards more feasible and efficient quantum technologies.

quant-ph↗

arXiv2024

QUBO-based SVM for credit card fraud detection on a real QPU

Among all the physical platforms for the realization of a Quantum Processing Unit (QPU), neutral atom devices are emerging as one of the main players. Their scalability, long coherence times, and the absence of manufacturing errors make them a viable candidate.. Here, we use a binary classifier model whose training is reformulated as a Quadratic Unconstrained Binary Optimization (QUBO) problem and implemented on a neutral atom QPU. In particular, we test it on a Credit Card Fraud (CCF) dataset. We propose several versions of the model, including exploiting the model in ensemble learning schemes. We show that one of our proposed versions seems to achieve higher performance and lower errors, validating our claims by comparing the most popular Machine Learning (ML) models with QUBO SVM models trained with ideal, noisy simulations and even via a real QPU. In addition, the data obtained via real QPU extend up to 24 atoms, confirming the model's noise robustness. We also show, by means of numerical simulations, how a certain amount of noise leads surprisingly to enhanced results. Our results represent a further step towards new quantum ML algorithms running on neutral atom QPUs for cybersecurity applications.

quant-ph↗

arXiv2024

Transfer learning with generative models for object detection on limited datasets

The availability of data is limited in some fields, especially for object detection tasks, where it is necessary to have correctly labeled bounding boxes around each object. A notable example of such data scarcity is found in the domain of marine biology, where it is useful to develop methods to automatically detect submarine species for environmental monitoring. To address this data limitation, the state-of-the-art machine learning strategies employ two main approaches. The first involves pretraining models on existing datasets before generalizing to the specific domain of interest. The second strategy is to create synthetic datasets specifically tailored to the target domain using methods like copy-paste techniques or ad-hoc simulators. The first strategy often faces a significant domain shift, while the second demands custom solutions crafted for the specific task. In response to these challenges, here we propose a transfer learning framework that is valid for a generic scenario. In this framework, generated images help to improve the performances of an object detector in a few-real data regime. This is achieved through a diffusion-based generative model that was pretrained on large generic datasets. With respect to the state-of-the-art, we find that it is not necessary to fine tune the generative model on the specific domain of interest. We believe that this is an important advance because it mitigates the labor-intensive task of manual labeling the images in object detection tasks. We validate our approach focusing on fishes in an underwater environment, and on the more common domain of cars in an urban setting. Our method achieves detection performance comparable to models trained on thousands of images, using only a few hundreds of input data. Our results pave the way for new generative AI-based protocols for machine learning applications in various domains.

cs.CV↗

arXiv2024

Quantum-Noise-Driven Generative Diffusion Models

Generative models realized with machine learning techniques are powerful tools to infer complex and unknown data distributions from a finite number of training samples in order to produce new synthetic data. Diffusion models are an emerging framework that have recently overcome the performance of the generative adversarial networks in creating synthetic text and high-quality images. Here, we propose and discuss the quantum generalization of diffusion models, i.e., three quantum-noise-driven generative diffusion models that could be experimentally tested on real quantum systems. The idea is to harness unique quantum features, in particular the non-trivial interplay among coherence, entanglement and noise that the currently available noisy quantum processors do unavoidably suffer from, in order to overcome the main computational burdens of classical diffusion models during inference. Hence, we suggest to exploit quantum noise not as an issue to be detected and solved but instead as a very remarkably beneficial key ingredient to generate much more complex probability distributions that would be difficult or even impossible to express classically, and from which a quantum processor might sample more efficiently than a classical one. An example of numerical simulations for an hybrid classical-quantum generative diffusion model is also included. Therefore, our results are expected to pave the way for new quantum-inspired or quantum-based generative diffusion algorithms addressing more powerfully classical tasks as data generation/prediction with widespread real-world applications ranging from climate forecasting to neuroscience, from traffic flow analysis to financial forecasting.

quant-ph↗

arXiv2024

Quantum AI for Alzheimer's disease early screening

Quantum machine learning is a new research field combining quantum information science and machine learning. Quantum computing technologies appear to be particularly well-suited for addressing problems in the health sector efficiently. They have the potential to handle large datasets more effectively than classical models and offer greater transparency and interpretability for clinicians. Alzheimer's disease is a neurodegenerative brain disorder that mostly affects elderly people, causing important cognitive impairments. It is the most common cause of dementia and it has an effect on memory, thought, learning abilities and movement control. This type of disease has no cure, consequently an early diagnosis is fundamental for reducing its impact. The analysis of handwriting can be effective for diagnosing, as many researches have conjectured. The DARWIN (Diagnosis AlzheimeR WIth haNdwriting) dataset contains handwriting samples from people affected by Alzheimer's disease and a group of healthy people. Here we apply quantum AI to this use-case. In particular, we use this dataset to test classical methods for classification and compare their performances with the ones obtained via quantum machine learning methods. We find that quantum methods generally perform better than classical methods. Our results pave the way for future new quantum machine learning applications in early-screening diagnostics in the healthcare domain.

cs.ET↗

arXiv2024

Permutation-equivariant quantum convolutional neural networks

The Symmetric group $S_{n}$ manifests itself in large classes of quantum systems as the invariance of certain characteristics of a quantum state with respect to permuting the qubits. The subgroups of $S_{n}$ arise, among many other contexts, to describe label symmetry of classical images with respect to spatial transformations, e.g. reflection or rotation. Equipped with the formalism of geometric quantum machine learning, in this work we propose the architectures of equivariant quantum convolutional neural networks (EQCNNs) adherent to $S_{n}$ and its subgroups. We demonstrate that a careful choice of pixel-to-qubit embedding order can facilitate easy construction of EQCNNs for small subgroups of $S_{n}$. Our novel EQCNN architecture corresponding to the full permutation group $S_{n}$ is built by applying all possible QCNNs with equal probability, which can also be conceptualized as a dropout strategy in quantum neural networks. For subgroups of $S_{n}$, our numerical results using MNIST datasets show better classification accuracy than non-equivariant QCNNs. The $S_{n}$-equivariant QCNN architecture shows significantly improved training and test performance than non-equivariant QCNN for classification of connected and non-connected graphs. When trained with sufficiently large number of data, the $S_{n}$-equivariant QCNN shows better average performance compared to $S_{n}$-equivariant QNN . These results contribute towards building powerful quantum machine learning architectures in permutation-symmetric systems.

quant-ph↗

arXiv2023

The role of data embedding in equivariant quantum convolutional neural networks

Geometric deep learning refers to the scenario in which the symmetries of a dataset are used to constrain the parameter space of a neural network and thus, improve their trainability and generalization. Recently this idea has been incorporated into the field of quantum machine learning, which has given rise to equivariant quantum neural networks (EQNNs). In this work, we investigate the role of classical-to-quantum embedding on the performance of equivariant quantum convolutional neural networks (EQCNNs) for the classification of images. We discuss the connection between the data embedding method and the resulting representation of a symmetry group and analyze how changing representation affects the expressibility of an EQCNN. We numerically compare the classification accuracy of EQCNNs with three different basis-permuted amplitude embeddings to the one obtained from a non-equivariant quantum convolutional neural network (QCNN). Our results show a clear dependence of classification accuracy on the underlying embedding, especially for initial training iterations. The improvement in classification accuracy of EQCNN over non-equivariant QCNN may be present or absent depending on the particular embedding and dataset used. It is expected that the results of this work can be useful to the community for a better understanding of the importance of data embedding choice in the context of geometric quantum machine learning.

quant-ph↗

arXiv2023

Efficient learning of arbitrary single-copy quantum states

Quantum state tomography is the problem of estimating a given quantum state. Usually, it is required to run the quantum experiment - state preparation, state evolution, measurement - several times to be able to estimate the output quantum state of the experiment, because an exponentially high number of copies of the state is required. In this work, we present an efficient algorithm to estimate with a small but non-zero probability of error the output state of the experiment using a single copy of the state, without knowing the evolution dynamics of the state. It also does not destroy the original state, which can be recovered easily for any further quantum processing. As an example, it is usually required to repeat a quantum image processing experiment many times, since many copies of the state of the output image are needed to extract the information from all its pixels. The information from $\mathcal{N}$ pixels of the image can be inferred from a single run of the image processing experiment in our algorithm, to efficiently estimate the density matrix of the image state.

physics.gen-ph↗

arXiv2023

Machine-learning based noise characterization and correction on neutral atoms NISQ devices

Neutral atoms devices represent a promising technology that uses optical tweezers to geometrically arrange atoms and modulated laser pulses to control the quantum states. A neutral atoms Noisy Intermediate Scale Quantum (NISQ) device is developed by Pasqal with rubidium atoms that will allow to work with up to 100 qubits. All NISQ devices are affected by noise that have an impact on the computations results. Therefore it is important to better understand and characterize the noise sources and possibly to correct them. Here, two approaches are proposed to characterize and correct noise parameters on neutral atoms NISQ devices. In particular the focus is on Pasqal devices and Machine Learning (ML) techniques are adopted to pursue those objectives. To characterize the noise parameters, several ML models are trained, using as input only the measurements of the final quantum state of the atoms, to predict laser intensity fluctuation and waist, temperature and false positive and negative measurement rate. Moreover, an analysis is provided with the scaling on the number of atoms in the system and on the number of measurements used as input. Also, we compare on real data the values predicted with ML with the a priori estimated parameters. Finally, a Reinforcement Learning (RL) framework is employed to design a pulse in order to correct the effect of the noise in the measurements. It is expected that the analysis performed in this work will be useful for a better understanding of the quantum dynamic in neutral atoms devices and for the widespread adoption of this class of NISQ devices.

quant-ph↗

arXiv2023

Deep learning enhanced noise spectroscopy of a spin qubit environment

The undesired interaction of a quantum system with its environment generally leads to a coherence decay of superposition states in time. A precise knowledge of the spectral content of the noise induced by the environment is crucial to protect qubit coherence and optimize its employment in quantum device applications. We experimentally show that the use of neural networks can highly increase the accuracy of noise spectroscopy, by reconstructing the power spectral density that characterizes an ensemble of carbon impurities around a nitrogen-vacancy (NV) center in diamond. Neural networks are trained over spin coherence functions of the NV center subjected to different Carr-Purcell sequences, typically used for dynamical decoupling (DD). As a result, we determine that deep learning models can be more accurate than standard DD noise-spectroscopy techniques, by requiring at the same time a much smaller number of DD sequences.

quant-ph↗

arXiv2023

Machine learning classification of non-Markovian noise disturbing quantum dynamics

In this paper machine learning and artificial neural network models are proposed for the classification of external noise sources affecting a given quantum dynamics. For this purpose, we train and then validate support vector machine, multi-layer perceptron and recurrent neural network models with different complexity and accuracy, to solve supervised binary classification problems. As a result, we demonstrate the high efficacy of such tools in classifying noisy quantum dynamics using simulated data sets from different realizations of the quantum system dynamics. In addition, we show that for a successful classification one just needs to measure, in a sequence of discrete time instants, the probabilities that the analysed quantum system is in one of the allowed positions or energy configurations. Albeit the training of machine learning models is here performed on synthetic data, our approach is expected to find application in experimental schemes, as e.g. for the noise benchmarking of noisy intermediate-scale quantum devices.

quant-ph↗