Quantum Computing has emerged as a viable alternative to classical computing for a number of different tasks, with the idea of a potential speedup in mind. One of the most promising fields of research in quantum computing is Quantum Machine Learning. An interesting area of application for Quantum Machine Learning can be found in High Energy Physics: one key component of creating experiments in a particle accelerator like the Large Hadron Collider is the simulation of those experiments beforehand, in order to gain a better understanding of the results actually measured. Those types of simulations, typically based on Monte-Carlo methods, require significant computing resources and, as we approach CERN's High Luminosity Phase, there is a strong need for more efficient and cost controlled simulations. In this thesis a model based on Quantum Generative Adversarial Networks (QGANs) is implemented, with the intention of exploring potential quantum computing advantages within a hybrid machine learning model that is tasked with the generation of calorimeter samples. The model is initially trained on an ideal simulator to ensure that the results are comparable to those of a similar classical model. Finally, the model is modified in order to effectively run on a real quantum device and the training is executed in its entirety on a 54-qubit quantum processor.
Quantum Computing has emerged as a viable alternative to classical computing for a number of different tasks, with the idea of a potential speedup in mind. One of the most promising fields of research in quantum computing is Quantum Machine Learning. An interesting area of application for Quantum Machine Learning can be found in High Energy Physics: one key component of creating experiments in a particle accelerator like the Large Hadron Collider is the simulation of those experiments beforehand, in order to gain a better understanding of the results actually measured. Those types of simulations, typically based on Monte-Carlo methods, require significant computing resources and, as we approach CERN's High Luminosity Phase, there is a strong need for more efficient and cost controlled simulations. In this thesis a model based on Quantum Generative Adversarial Networks (QGANs) is implemented, with the intention of exploring potential quantum computing advantages within a hybrid machine learning model that is tasked with the generation of calorimeter samples. The model is initially trained on an ideal simulator to ensure that the results are comparable to those of a similar classical model. Finally, the model is modified in order to effectively run on a real quantum device and the training is executed in its entirety on a 54-qubit quantum processor.
Abstract The prospect of quantum computing with a potential exponential speed-up compared to classical computing identifies it as a promising method in the search for alternative future High Energy Physics (HEP) simulation approaches. HEP simulations, such as employed at the Large Hadron Collider at CERN, are extraordinarily complex and require an immense amount of computing resources in hardware and time. For some HEP simulations, classical machine learning models have already been successfully developed and tested, resulting in several orders of magnitude speed-up. In this research, we proceed to the next step and explore whether quantum computing can provide sufficient accuracy, and further improvements, suggesting it as an exciting direction of future investigations. With a small prototype model, we demonstrate a full quantum Generative Adversarial Network (GAN) model for generating downsized eight-pixel calorimeter shower images. The advantage over previous quantum models is that the model generates real individual images containing pixel energy values instead of simple probability distributions averaged over a test sample. To complete the picture, the results of the full quantum GAN model are compared to hybrid quantum-classical models using a classical discriminator neural network.
Quantum Machine Learning (qML) is one of the most promising and very intuitive applications onnear-term quantum devices which possess the potential to combat computing resource challengesfaster than traditional computers. Classical Machine Learning (ML) is taking up a significant role inparticle physics to speed up detector simulations. Generative Adversarial Networks (GANs) haveproven to achieve a similar level of accuracy compared to Monte Carlo-based simulations whiledecreasing the computation time by orders of magnitude. In this research we are moving on and applyquantum computing to GAN-based detector simulations.Given the limitations of current quantum hardware in terms of number of qubits, connectivity, andnoise, we perform initial tests with a simplified GAN model running on quantum simulators. Themodel is a classical-quantum hybrid ansatz. It consists of a quantum generator, defined as aparameterised circuit based on single and two qubit gates, combined with a classical discriminator.Our initial qGAN prototype focuses on a one-dimensional toy-distribution, representing the energydeposited in a detector by a single particle. It employs three qubits and achieves high physics accuracythanks to hyper-parameter optimisation. Furthermore, we study the influence of real hardware noisefor the qML GAN training. A second qGAN is developed to simulate 2D images with a 64-pixelresolution, representing the energy deposition patterns in the detector. Different quantum ansatzes arestudied. We obtained the best results using a tree-tensor-network architecture with six qubits.Additionally, we discuss challenges and potential benefits of quantum computing as well as our plansfor future developments.
This paper investigates the application of Quantum Generative Adversarial Networks (QGANs) to data augmentation for machine learning. Traditional Generative Adversarial Networks (GANs) rely on classical neural networks, while this research explores leveraging quantum circuits as generators within a QGAN architecture. The core idea is to train a quantum generator to produce synthetic data samples, supplementing existing datasets with novel instances. The discriminator remains a classical neural network, tasked with distinguishing between real and generated data. We present a theoretical framework for this approach, outlining the mathematical formulation and key components. Specifically, we introduce the notation (x, s_1, s_2, ..., s_K) to represent data samples, generator states, and relevant parameters. The objective function for the QGAN is defined as minimizing the Jensen-Shannon divergence between the real and generated data distributions. The effectiveness of this approach is discussed, highlighting potential advantages and challenges. This work contributes to the emerging field of quantum machine learning and offers a novel strategy for improving the performance of machine learning models, particularly in scenarios with limited training data.
The increasing demands on simulation statistics for HL-LHC analyses challenge the scalability of traditional calorimeter simulation within all LHC collaborations. Fast simulation techniques based on machine learning have proven effective, yet further improvement may arise from quantum-inspired models. In this study we investigate the feasibility of integrating Quantum Neural Network (QNN) components into the ATLAS fast calorimeter simulation framework, to evaluate potential gain in generative performance and generalisation. We focus on a hybrid pipeline where a quantum Generative Adversarial Network (qGAN) is employed, whose generator is composed of a Parametrised Quantum Circuit (PQC) followed by a classical neural network, while the discriminator is kept classical. We report on implementation details, benchmarking against established fast simulation components, and performance metrics. Preliminary results show that qGAN models are technically feasible within ATLAS software and are promising for benefit with respect to the classical ATLAS fast simulation system.
Quantum generative adversarial networks (QGANs) represent a significant advancement at the intersection of quantum computing and machine learning, offering novel approaches to data encoding and generation for next-generation quantum applications. This chapter provides a comprehensive examination of QGANs, exploring their fundamental architecture, implementation strategies, and potential applications. We detail how QGANs leverage quantum physics principles to potentially outperform classical generative adversarial networks (GANs), particularly in scenarios requiring quantum data processing and quantum-enhanced computations. The study outlines the critical differences between classical GANs and QGANs, focusing on their unique quantum circuit-based generator quantum circuit-based generator and discriminator components. We present an in-depth analysis of quantum data encoding techniques, including state representation, preparation methods, and various encoding scheme encoding scheme s such as amplitude, basis, and phase encoding. The chapter also addresses the challenges in QGAN implementation, discussing scalability issues, noise management, and resource optimization strategies. Special attention is given to training methodologies, including hybrid quantum-classical approaches and specialized loss functions for quantum systems. Furthermore, we explore practical applications across multiple domains, including quantum machine learning, quantum simulation, and quantum cryptography. Real-world case studies in financial modeling financial modeling , healthcare, and cybersecurity demonstrate the practical potential of QGANs. The chapter concludes by identifying future research directions and opportunities for advancing QGAN technology, emphasizing the importance of interdisciplinary collaboration in developing more sophisticated and practical quantum computing solutions.
Understanding the information processing in neuronal networks relies on the development of computational models that accurately reproduce their activity data. Machine learning techniques have shown promising results in generating synthetic neuronal data, but interpretability remains an issue due to a large number of parameters requiring fitting. Quantum machine learning models, particularly quantum generative learning, are emerging as more compact alternatives that offer similar outcomes. This study presents an efficient framework for generating synthetic neuronal data using a Quantum Generative Adversarial Network (QGAN), with a quantum generator and a classical discriminator. We tested the proposed framework for the minimal case of two neurons, considering the case of single time-steps. Preliminary results demonstrate the QGAN's capability to achieve reliable outcomes with a reduced number of trainable parameters, scaling efficiently for increasing neuronal network sizes. The model effectively captures spiking frequencies of real data, although further refinement is required to incorporate temporal correlations for more extended time-steps. Despite certain limitations, this study lays the foundation for future advancements in using quantum adversarial generative networks to model neuronal activity. The promising potential of QGANs in this domain highlights the possibility of gaining valuable insights into the functioning of complex biological systems through quantum-inspired computational methods.