Benchmarking of quantum machine learning (QML) algorithms is challenging due to the complexity and variability of QML systems, e. g., regarding model ansatzes, data sets, training techniques, and hyper-parameter selection. The QUantum computing Application benchmaRK (QUARK) framework simplifies and standardizes benchmarking studies for quantum computing applications. Here, we propose several extensions of QUARK to include the ability to evaluate the training and deployment of quantum generative models. We describe the updated software architecture and illustrate its flexibility through several example applications: (1) We trained different quantum generative models using several circuit ansatzes, data sets, and data transformations. (2) We evaluated our models on GPU and real quantum hardware. (3) We assessed the generalization capabilities of our generative models using a broad set of metrics that capture, e. g., the novelty and validity of the generated data.
Benchmarking of quantum machine learning (QML) algorithms is challenging due to the complexity and variability of QML systems, e. g., regarding model ansatzes, data sets, training techniques, and hyper-parameter selection. The QUantum computing Application benchmaRK (QUARK) framework simplifies and standardizes benchmarking studies for quantum computing applications. Here, we propose several extensions of QUARK to include the ability to evaluate the training and deployment of quantum generative models. We describe the updated software architecture and illustrate its flexibility through several example applications: (1) We trained different quantum generative models using several circuit ansatzes, data sets, and data transformations. (2) We evaluated our models on GPU and real quantum hardware. (3) We assessed the generalization capabilities of our generative models using a broad set of metrics that capture, e. g., the novelty and validity of the generated data.
Abstract Quantum computing promises a disruptive impact on machine learning algorithms, taking advantage of the exponentially large Hilbert space available. However, it is not clear how to scale quantum machine learning (QML) to industrial-level applications. This paper investigates the scalability and noise resilience of quantum generative learning applications. We consider the training performance in the presence of statistical noise due to finite-shot noise statistics and quantum noise due to decoherence to analyze the scalability of QML methods. We employ rigorous benchmarking techniques to track progress and identify challenges in scaling QML algorithms, and show how characterization of QML systems can be accelerated, simplified, and made reproducible when the QUARK framework is used. We show that QGANs are not as affected by the curse of dimensionality as QCBMs and to which extent QCBMs are resilient to noise.
Quantum generative modeling is a growing area of interest for industry-relevant applications. This work systematically compares a broad range of techniques to guide quantum computing practitioners when deciding which models and methods to use in their applications. We compare fundamentally different architectural ansatzes of parametric quantum circuits: (1) A continuous architecture, which produces continuous-valued data samples, and (2) a discrete architecture, which samples on a discrete grid. We also compare the performance of different data transformations: the min-max and the probability integral transforms. We use two popular training methods: (1) quantum circuit Born machines (QCBM), and (2) quantum generative adversarial networks (QGAN). We study their performance and tradeoffs as the number of model parameters increases, with a baseline comparison of similarly trained classical neural networks. The study is performed on six low-dimensional synthetic and two real financial data sets. Our two key findings are that: (1) For all data sets, our quantum models require similar or fewer parameters than their classical counterparts. In the extreme case, the quantum models require two orders of magnitude less parameters. (2) We empirically find that a variant of the discrete architecture, which learns the copula of the probability distribution, outperforms all other methods.
Advancements in quantum computing have sparked a systematic evaluation of quantum machine learning (QML) models, focusing on their behavior and performance across diverse learning tasks such as classification, regression, generative modeling, and feature compression. The primary focus is on assessing the performance and behavior of various QML architectures-including Quantum Neural Networks (QNNs), Quantum Support Vector Classifiers (QSVCs), Quantum Generative Adversarial Networks (QGANs), Quantum Convolutional Neural Networks (QCNNs), and Quantum Autoencoders (QAEs)-implemented using Qiskit's machine learning library. This evaluation is conducted using an existing benchmarking framework that ensures consistent experimental conditions and supports flexible evaluation strategies. To provide additional context and insight, these quantum models are compared against classical counterparts using widely adopted implementations. Experiments are carried out on a range of datasets, including structured and low-dimensional examples like Bars and Stripes, as well as more complex datasets like Downscaled MNIST and synthetic Hyperplanes. By providing a standardized evaluation of these models within the Qiskit framework, this study establishes a reproducible performance baseline and highlights key challenges for QML systems in the noisy intermediate-scale quantum (NISQ) era.
The integration of quantum computing and machine learning has ushered in a transformative era in data analysis, characterized by the development of Quantum Machine Learning (QML). This chapter explores the pivotal role of standardization in evaluation practices within QML research, addressing the challenges posed by inconsistent metrics, diverse benchmarking standards, and reproducibility concerns. Emphasis was placed on the establishment of unified evaluation metrics tailored to quantum algorithms, which can enhance the comparability of results across studies. Additionally, the chapter advocates for the creation of standardized benchmarking frameworks and reproducibility guidelines to bolster the reliability of QML findings. Collaborative initiatives within the research community are encouraged to promote knowledge sharing and best practices. By fostering standardized evaluation practices, this chapter aims to enhance the credibility and impact of QML research, paving the way for innovative advancements in various applications, including finance, healthcare, and artificial intelligence.
As the limits of classical machine learning (ML) become increasingly evident—especially in terms of computational scalability and data processing—quantum computing emerges as a promising frontier capable of addressing these challenges. Quantum Machine Learning (QML) represents the intersection of quantum computing and traditional ML, aiming to leverage quantum phenomena such as superposition, entanglement, and quantum parallelism to enhance learning capabilities, accelerate training, and solve complex problems that are intractable for classical algorithms. This paper provides a comprehensive overview of the evolving field of QML, beginning with the theoretical foundations of quantum computing and its synergy with classical machine learning principles. We explore key QML algorithms, including quantum support vector machines (QSVM), variational quantum classifiers (VQC), quantum neural networks (QNN), and hybrid quantum-classical approaches that exemplify the practical integration of both paradigms. We further examine real-world applications of QML across domains such as drug discovery, finance, climate modeling, and optimization, where quantum enhancements have begun to show early but promising results. Despite its theoretical potential, QML faces substantial limitations, including quantum hardware instability, limited qubit scalability, noise sensitivity, and unresolved challenges in quantum data encoding and interpretability. In synthesizing recent advancements and persistent obstacles, this paper highlights the importance of continued interdisciplinary research, algorithmic refinement, and hardware evolution. We also outline future directions that could lead QML from experimental promise to practical utility, including developments in quantum error correction, benchmarking standards, and application-specific quantum architectures
As the quantum computing community gravitates towards understanding the practical benefits of quantum computers, having a clear definition and evaluation scheme for assessing practical quantum advantage in the context of specific applications is paramount. Generative modeling, for example, is a widely accepted natural use case for quantum computers, and yet has lacked a concrete approach for quantifying success of quantum models over classical ones. In this work, we construct a simple and unambiguous approach to probe practical quantum advantage for generative modeling by measuring the algorithm's generalization performance. Using the sample-based approach proposed here, any generative model, from state-of-the-art classical generative models such as generative adversarial networks (GANs) to quantum models such as quantum circuit born machines, can be evaluated under the same conditions on a concrete well-defined framework. In contrast to other sample-based metrics for probing practical generalization, we leverage constrained optimization problems (e.g., cardinality-constrained problems) and use these discrete datasets to define specific metrics capable of unambiguously measuring the quality of the samples and the model's generalization capabilities for generating data beyond the training set, but still within the valid solution space. Additionally, our metrics can diagnose trainability issues such as mode collapse and overfitting, as we illustrate when comparing GANs to quantum-inspired models built out of tensor networks. Our simulation results show that our quantum-inspired models have up to a 68 times enhancement in generating unseen unique and valid samples compared to the GANs explored here, and a ratio of 61:2 for generating samples with better quality than those observed in the training set. We foresee these metrics as valuable tools for rigorously defining practical quantum advantage in the domain of generative modeling, where finding a winning model remains an ongoing challenge as new architectures are developed.