Abstract Quantum machine learning (QML) presents potential for early industrial adoption, yet limited access to quantum hardware remains a significant bottleneck for deployment of QML solutions. This work explores the use of classical surrogates to bypass this restriction, which is a technique that allows to build a lightweight classical representation of a (trained) quantum model, enabling to perform inference on entirely classical devices. We reveal prohibitive high computational demand associated with previously proposed methods for generating classical surrogates from quantum models, and propose an alternative pipeline enabling generation of classical surrogates at a larger scale than was previously possible. Previous methods required at least a high-performance computing (HPC) system for quantum models of below industrial scale (ca. 20 qubits), which raises questions about its practicality. We greatly minimize the redundancies of the previous approach, utilizing only a minute fraction of the resources previously needed. We demonstrate the effectiveness of our method on a real-world energy demand forecasting problem, conducting rigorous testing of performance and computation demand in both simulations and on quantum hardware. Our results indicate that our method achieves high accuracy on the testing dataset while its computational resource requirements scale polynomially rather than exponentially. This work presents a lightweight approach to transform quantum solutions into classically deployable versions, facilitating faster integration of quantum technology in industrial settings. Furthermore, it can serve as a powerful research tool in search of a practical quantum advantage in an empirical setup.
Abstract Quantum machine learning (QML) presents potential for early industrial adoption, yet limited access to quantum hardware remains a significant bottleneck for deployment of QML solutions. This work explores the use of classical surrogates to bypass this restriction, which is a technique that allows to build a lightweight classical representation of a (trained) quantum model, enabling to perform inference on entirely classical devices. We reveal prohibitive high computational demand associated with previously proposed methods for generating classical surrogates from quantum models, and propose an alternative pipeline enabling generation of classical surrogates at a larger scale than was previously possible. Previous methods required at least a high-performance computing (HPC) system for quantum models of below industrial scale (ca. 20 qubits), which raises questions about its practicality. We greatly minimize the redundancies of the previous approach, utilizing only a minute fraction of the resources previously needed. We demonstrate the effectiveness of our method on a real-world energy demand forecasting problem, conducting rigorous testing of performance and computation demand in both simulations and on quantum hardware. Our results indicate that our method achieves high accuracy on the testing dataset while its computational resource requirements scale polynomially rather than exponentially. This work presents a lightweight approach to transform quantum solutions into classically deployable versions, facilitating faster integration of quantum technology in industrial settings. Furthermore, it can serve as a powerful research tool in search of a practical quantum advantage in an empirical setup.
Abstract - The exponential growth of large-scale data has created significant challenges in storage, processing, and optimization that classical computing systems struggle to address efficiently. Quantum Machine Learning (QML) has emerged as a promising paradigm that integrates quantum computing concepts with machine learning techniques to tackle complex big data optimization problems. By utilizing quantum features such as superposition, entanglement, and parallelism, QML algorithms can accelerate tasks like clustering, classification, and dimensionality reduction, which are traditionally computationally demanding. Recent advancements indicate strong potential for quantum-inspired optimization in fields including cybersecurity, financial portfolio management, Industry 4.0, and healthcare analytics. This paper provides a comprehensive survey of QML algorithms designed for big data optimization, examining their advantages, limitations, and application domains. Additionally, it discusses the performance trade-offs associated with hybrid quantum–classical frameworks and highlights future research directions aimed at creating secure, scalable, and resource-efficient quantum solutions for large-scale, data-driven decision-making. As data volumes continue to expand at extremely rapid rates, processing big data with traditional machine learning (ML) techniques has become increasingly challenging. ML models often struggle with issues related to computational power, efficient parameter tuning, accurate model selection, and maintaining high performance when dealing with massive datasets. Deep learning approaches—such as convolutional neural networks (CNNs)—demand substantial computational resources to train on large-scale supervised learning tasks. Moreover, the difficulty of training these networks grows significantly as the size and complexity of the datasets increase. In response to these limitations, Quantum Machine Learning (QML) has emerged as a promising research domain at the intersection of quantum computing and machine learning. Quantum computers operate fundamentally differently from classical systems, using the principles of quantum mechanics to encode and process information. As a result, quantum computational methods have the potential to address certain problems that are computationally intensive or infeasible for classical machines. Index Terms— Quantum Machine Learning (QML); Big Data Optimization; Quantum Algorithms; Hybrid Quantum-Classical Models; Quantum Computing; Data Analytics
Quantum Machine Learning (QML) has emerged as a transformative paradigm that integrates the computational advantages of quantum computing with the adaptive intelligence of machine learning to solve complex optimization problems in smart computing systems. Traditional optimization techniques often struggle with high-dimensional search spaces, combinatorial complexity, computational overhead, and scalability limitations in applications such as intelligent transportation, healthcare analytics, smart manufacturing, cybersecurity, cloud computing, and Internet of Things (IoT) infrastructures. QML approaches exploit quantum superposition, entanglement, and quantum parallelism to accelerate optimization tasks and enhance predictive performance beyond classical machine learning capabilities. This research proposes a hybrid Quantum Machine Learning optimization framework that combines Variational Quantum Circuits (VQCs), Quantum Neural Networks (QNNs), and classical deep learning models to address resource allocation, task scheduling, energy optimization, and intelligent decision-making in smart computing environments. The proposed framework integrates quantum-enhanced feature extraction, adaptive optimization layers, and reinforcement-based learning mechanisms to improve convergence speed and computational efficiency. Experimental analysis is performed using benchmark optimization datasets and simulated quantum environments to evaluate accuracy, execution time, energy efficiency, and scalability. Comparative results demonstrate that the proposed QML-based framework achieves superior optimization accuracy, reduced computational latency, and improved resource utilization when compared with traditional machine learning and classical metaheuristic optimization methods. Furthermore, the study highlights the practical significance of hybrid quantum-classical architectures in next-generation intelligent systems where large-scale optimization and real-time decision support are critical. The findings suggest that QML can significantly contribute to the advancement of sustainable, adaptive, and high-performance smart computing ecosystems while opening new directions for future quantum-aware intelligent infrastructures.
Quantum algorithms for partial differential equations (PDEs) face severe practical constraints on near-term hardware: limited qubit counts restrict spatial resolution to coarse grids, while circuit depth limitations prevent accurate long-time integration. These hardware bottlenecks confine quantum PDE solvers to low-fidelity regimes despite their theoretical potential for computational speedup. We introduce a multifidelity learning framework that corrects coarse quantum solutions to high-fidelity accuracy using sparse classical training data, facilitating the path toward practical quantum utility for scientific computing. The approach trains a low-fidelity surrogate on abundant quantum solver outputs, then learns correction mappings through a multifidelity neural architecture that balances linear and nonlinear transformations. Demonstrated on benchmark nonlinear PDEs including viscous Burgers equation and incompressible Navier-Stokes flows via quantum lattice Boltzmann methods, the framework successfully corrects coarse quantum predictions and achieves temporal extrapolation well beyond the classical training window. This strategy illustrates how one can reduce expensive high-fidelity simulation requirements while producing predictions that are competitive with classical accuracy. By bridging the gap between hardware-limited quantum simulations and application requirements, this work establishes a pathway for extracting computational value from current quantum devices in real-world scientific applications, advancing both algorithm development and practical deployment of near-term quantum computing for computational physics.
Abstract Quantum Machine Learning (QML) represents a transformative paradigm that leverages quantum mechanical principles to enhance computational optimization in complex systems beyond the capabilities of classical machine learning algorithms. This paper investigates the optimization advantages of QML through a comprehensive analysis of quantum neural networks, quantum support vector machines, and hybrid quantum-classical architectures applied to complex system optimization problems. Our methodology employs variational quantum circuits with optimized feature encoding strategies and compares performance against classical baselines across multiple complexity scales. Experimental results demonstrate that QML algorithms achieve superior accuracy (95.1% for hybrid approaches vs 89.5% for classical neural networks), faster convergence rates (10x improvement in optimization iterations), and exponential scalability advantages for large-scale problems (31.7x speedup for problems with 5000 + parameters). The findings reveal that quantum algorithms excel in exploring high-dimensional solution spaces through superposition and entanglement, enabling more efficient navigation of complex optimization landscapes. Key contributions include a novel hybrid quantum-classical optimization framework, systematic performance benchmarking across problem complexities, and identification of quantum advantage thresholds for practical deployment. Results indicate that QML provides significant computational benefits for complex system optimization, particularly in scenarios involving large parameter spaces, non-convex optimization landscapes, and real-time processing requirements.
The advent of noisy intermediate-scale quantum computers has put the search for possible applications to the forefront of quantum information science. One area where hopes for an advantage through near-term quantum computers are high is quantum machine learning, where variational quantum learning models based on parametrized quantum circuits are discussed. In this work, we introduce the concept of a classical surrogate, a classical model which can be efficiently obtained from a trained quantum learning model and reproduces its input-output relations. As inference can be performed classically, the existence of a classical surrogate greatly enhances the applicability of a quantum learning strategy. However, the classical surrogate also challenges possible advantages of quantum schemes. As it is possible to directly optimize the Ansatz of the classical surrogate, they create a natural benchmark the quantum model has to outperform. We show that large classes of well-analyzed reuploading models have a classical surrogate. We conducted numerical experiments and found that these quantum models show no advantage in performance or trainability in the problems we analyze. This leaves only generalization capability as a possible point of quantum advantage and emphasizes the dire need for a better understanding of inductive biases of quantum learning models.
The advent of noisy intermediate-scale quantum computers has put the search for possible applications to the forefront of quantum information science. One area where hopes for an advantage through near-term quantum computers are high is quantum machine learning, where variational quantum learning models based on parametrized quantum circuits are discussed. In this work, we introduce the concept of a classical surrogate, a classical model which can be efficiently obtained from a trained quantum learning model and reproduces its input-output relations. As inference can be performed classically, the existence of a classical surrogate greatly enhances the applicability of a quantum learning strategy. However, the classical surrogate also challenges possible advantages of quantum schemes. As it is possible to directly optimize the Ansatz of the classical surrogate, they create a natural benchmark the quantum model has to outperform. We show that large classes of well-analyzed reuploading models have a classical surrogate. We conducted numerical experiments and found that these quantum models show no advantage in performance or trainability in the problems we analyze. This leaves only generalization capability as a possible point of quantum advantage and emphasizes the dire need for a better understanding of inductive biases of quantum learning models.