Generative invertible quantum neural networks

Rousselot, Armand; Spannowsky, Michael

Abstract

Invertible Neural Networks (INN) have become established tools for the simulation and generation of highly complex data. We propose a quantum-gate algorithm for a Quantum Invertible Neural Network (QINN) and apply it to the LHC data of jet-associated production of a Z-boson that decays into leptons, a standard candle process for particle collider precision measurements. We compare the QINN's performance for different loss functions and training scenarios. For this task, we find that a hybrid QINN matches the performance of a significantly larger purely classical INN in learning and generating complex data.

Citation

Rousselot, A., & Spannowsky, M. (2024). Generative invertible quantum neural networks. SciPost Physics, 16(6), Article 146. https://doi.org/10.21468/scipostphys.16.6.146

• Journal Article Type: Article
• Acceptance Date: Feb 22, 2024
• Online Publication Date: Jun 4, 2024
• Publication Date: 2024
• Deposit Date: Jul 11, 2024
• Publicly Available Date: Jul 11, 2024
• Journal: SciPost Physics
• Print ISSN: 2542-4653
• Publisher: SciPost
• Peer Reviewed: Peer Reviewed
• Volume: 16
• Issue: 6
• Article Number: 146
• DOI: https://doi.org/10.21468/scipostphys.16.6.146
• Public URL: https://durham-repository.worktribe.com/output/2524987