Style-based quantum generative adversarial networks for Monte Carlo events

Abstract

We propose and assess an alternative quantum generator architecture in the context of generative adversarial learning for Monte Carlo event generation, used to simulate particle physics processes at the Large Hadron Collider (LHC). We validate this methodology by implementing the quantum network on artificial data generated from known underlying distributions. The network is then applied to Monte Carlo-generated datasets of specific LHC scattering processes. The new quantum generator architecture leads to a generalization of the state-of-the-art implementations, achieving smaller Kullback-Leibler divergences even with shallow-depth networks. Moreover, the quantum generator successfully learns the underlying distribution functions even if trained with small training sample sets; this is particularly interesting for data augmentation applications. We deploy this novel methodology on two different quantum hardware architectures, trapped-ion and superconducting technologies, to test its hardware-independent viability.

15 pages, 10 figures, accepted in Quantum, code available in https://github.com/QTI-TH/style-qgan

References in corpus (10)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• ADADELTA: An Adaptive Learning Rate Method
• Quantum algorithm for solving linear systems of equations
• Quantum computational advantage using photons
• Quantum Data Fitting
• Data Augmentation Using GANs
• Determining the proton content with a quantum computer
• Single-qubit universal classifier implemented on an ion-trap quantum device
• Quantum Generative Adversarial Networks in a Continuous-Variable Architecture to Simulate High Energy Physics Detectors

Cited by in corpus (23)

• Understanding quantum machine learning also requires rethinking generalization
• Machine Learning for Anomaly Detection in Particle Physics
• Quantum Anomaly Detection for Collider Physics
• Trainability barriers and opportunities in quantum generative modeling
• Classical versus Quantum: comparing Tensor Network-based Quantum Circuits on LHC data
• A performance characterization of quantum generative models
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Unsupervised Quantum Circuit Learning in High Energy Physics
• ELSA -- Enhanced latent spaces for improved collider simulations
• Quantum-probabilistic Hamiltonian learning for generative modelling & anomaly detection
• Conditional Born machine for Monte Carlo event generation
• Qibolab: an open-source hybrid quantum operating system
• Towards Efficient Quantum Hybrid Diffusion Models
• Long-lived Particles Anomaly Detection with Parametrized Quantum Circuits
• Quantum simulation of colour in perturbative quantum chromodynamics
• Jet Discrimination with Quantum Complete Graph Neural Network
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions
• Guided Quantum Compression for High Dimensional Data Classification
• Generative Invertible Quantum Neural Networks
• Cross-platform hardware benchmark of style-based quantum GANs for data augmentation on superconducting and trapped-ion processors
• Determining probability density functions with adiabatic quantum computing
• A general approach to quantum integration of cross sections in high-energy physics
• Double-bracket quantum algorithms for high-fidelity ground state preparation