Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Symposium on Grids and Clouds (ISGC)

Quantum Invertible Neural Networks for Fast Calorimetry as Quantum Generative Model with high interpretability at Future Colliders

Matteo Franchini, Federico Corchia

Published Oct 21, 2026• 0 citations
Publisher

Abstract

The fast calorimeter simulation is a critical computational bottleneck for the ATLAS experiment atthe High-Luminosity LHC and for the design of future colliders. Invertible Neural Networks (INNs) andnormalizingflowshavedemonstratedimpressiveaccuracyasgenerativemodelsforcalorimeter shower simulation, forming the backbone of the emerging FastCaloSim framework. In this work we explore the extension of this classical approach toward quantum-conditioned invertible neural networks (qINN). We present the conceptual motivation, discuss the fundamental tension between the unitarity of quantum circuits and the irreversibility of projective measurement, and out line two complementary solution strategies. As a first feasibility study we implement a hybrid architectureinwhichasmallquantumcircuitreplacestheclassicalconditioningsub-network inside an otherwise classicalINN, trained on ATLAS Open-Data pion showers from the FastCalorimeter Challenge dataset. The preliminary results, obtained with a 6-qubit, 2-layer variational ansatz, show encouraging convergence and motivate further optimisation. The work is a feasibility study; no definitive performance claims are made.

DOI
10.22323/1.523.0022

Related papers

Feasibility Study of QNN-Based Latent Space Generation for Fast Calorimeter Simulation in ATLAS

Federico Andrea Corchia, Matteo Franchini

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.

International Symposium on Grids and Clouds (ISGC)•Oct 21, 2026•0 citations

CaloQVAE for electromagnetic shower synthetic data generation in the ATLAS calorimeter

Wojciech T. Fedorko

As CERN approaches the High-Luminosity LHC (HL-LHC) run, the computational cost of first-principles detector simulation has become a critical bottleneck, with projections indicating millions of CPU-years required to generate the necessary Monte Carlo datasets — a substantial share of which is consumed by calorimeter shower simulation. Building on our earlier proof-of-concept demonstrating Quantum-assisted Generative AI for synthetic calorimetry data generation, we present what is, to our knowledge, the first full-scale demonstration of this approach applied to ATLAS detector simulated data. Our model couples a Restricted Boltzmann Machine (RBM), mapped onto the logical qubit topology of D-Wave's quantum annealing processor, with a deep generative architecture to produce realistically scaled calorimeter showers. We extend our earlier framework with several techniques critical to scaling the approach to production-grade ATLAS geometry and granularity: advanced prior conditioning strategies, Spin Reversal Transforms to mitigate intrinsic qubit biases, orbit averaging to reduce sampling noise, and QPU-aware weight normalization to stabilize the sampling process. We show how these advances yield quantum processor generated calorimeter datasets that maintain high fidelity in physics features relative to first-principles GEANT4 simulation while promising substantial improvements in generation throughput over both traditional simulation and purely classical deep learning generative models. We discuss the implications of these results for scaling quantum-assisted generative modeling to full ATLAS fast-simulation pipelines ahead of the HL-LHC era.

•Sep 25, 2026•0 citations

Generative invertible quantum neural networks

Armand Rousselot, Michael Spannowsky

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.

arXiv:2302.12906•SciPost Physics•Jun 4, 2024•6 citations

A Quantum Generative Adversarial Network model for the Simulation of LHC Calorimeter Data

PHILIP CORSINI

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.

•Apr 15, 2026•0 citations

Quantum-Assisted Generative AI for Simulation of the Calorimeter Response

Wojciech T. Fedorko, J. Quetzalcóatl Toledo-Marín, Geoffrey Fox +7 more

As CERN approaches the launch of the High Luminosity Large Hadron Collider (HL-LHC) by the decade’s end, the computational demands of traditional simulations have become untenably high. Projections show millions of CPU-years required to create simulated datasets - with a substantial fraction of CPU time devoted to calorimetric simulations. This presents unique opportunities for breakthroughs in computational physics. We show how Quantumassisted Generative AI can be used for the purpose of creating synthetic, realistically scaled calorimetry dataset. The model is constructed by combining D-Wave’s Quantum Annealer processor with a Deep Learning architecture, increasing the timing performance with respect to first principles simulations and Deep Learning models alone, while maintaining current state-of-the-art data quality

EPJ Web of Conferences•Jan 1, 2025•0 citations

Quantum-Assisted Generative AI for Simulation of the Calorimeter Response

Wojciech T. Fedorko, J. Quetzalcóatl Toledo-Marín, Geoffrey Fox +7 more

As CERN approaches the launch of the High Luminosity Large Hadron Collider (HL-LHC) by the decade’s end, the computational demands of traditional simulations have become untenably high. Projections show millions of CPU-years required to create simulated datasets - with a substantial fraction of CPU time devoted to calorimetric simulations. This presents unique opportunities for breakthroughs in computational physics. We show how Quantumassisted Generative AI can be used for the purpose of creating synthetic, realistically scaled calorimetry dataset. The model is constructed by combining D-Wave’s Quantum Annealer processor with a Deep Learning architecture, increasing the timing performance with respect to first principles simulations and Deep Learning models alone, while maintaining current state-of-the-art data quality

•Oct 7, 2025•0 citations
The fast calorimeter simulation is a critical computational bottleneck for the ATLAS experiment atthe High-Luminosity LHC and for the design of future colliders. Invertible Neural Networks (INNs) andnormalizingflowshavedemonstratedimpressiveaccuracyasgenerativemodelsforcalorimeter shower simulation, forming the backbone of the emerging FastCaloSim framework. In this work we explore the extension of this classical approach toward quantum-conditioned invertible neural networks (qINN). We present the conceptual motivation, discuss the fundamental tension between the unitarity of quantum circuits and the irreversibility of projective measurement, and out line two complementary solution strategies. As a first feasibility study we implement a hybrid architectureinwhichasmallquantumcircuitreplacestheclassicalconditioningsub-network inside an otherwise classicalINN, trained on ATLAS Open-Data pion showers from the FastCalorimeter Challenge dataset. The preliminary results, obtained with a 6-qubit, 2-layer variational ansatz, show encouraging convergence and motivate further optimisation. The work is a feasibility study; no definitive performance claims are made.
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.
As CERN approaches the High-Luminosity LHC (HL-LHC) run, the computational cost of first-principles detector simulation has become a critical bottleneck, with projections indicating millions of CPU-years required to generate the necessary Monte Carlo datasets — a substantial share of which is consumed by calorimeter shower simulation. Building on our earlier proof-of-concept demonstrating Quantum-assisted Generative AI for synthetic calorimetry data generation, we present what is, to our knowledge, the first full-scale demonstration of this approach applied to ATLAS detector simulated data. Our model couples a Restricted Boltzmann Machine (RBM), mapped onto the logical qubit topology of D-Wave's quantum annealing processor, with a deep generative architecture to produce realistically scaled calorimeter showers. We extend our earlier framework with several techniques critical to scaling the approach to production-grade ATLAS geometry and granularity: advanced prior conditioning strategies, Spin Reversal Transforms to mitigate intrinsic qubit biases, orbit averaging to reduce sampling noise, and QPU-aware weight normalization to stabilize the sampling process. We show how these advances yield quantum processor generated calorimeter datasets that maintain high fidelity in physics features relative to first-principles GEANT4 simulation while promising substantial improvements in generation throughput over both traditional simulation and purely classical deep learning generative models. We discuss the implications of these results for scaling quantum-assisted generative modeling to full ATLAS fast-simulation pipelines ahead of the HL-LHC era.
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.
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.
As CERN approaches the launch of the High Luminosity Large Hadron Collider (HL-LHC) by the decade’s end, the computational demands of traditional simulations have become untenably high. Projections show millions of CPU-years required to create simulated datasets - with a substantial fraction of CPU time devoted to calorimetric simulations. This presents unique opportunities for breakthroughs in computational physics. We show how Quantumassisted Generative AI can be used for the purpose of creating synthetic, realistically scaled calorimetry dataset. The model is constructed by combining D-Wave’s Quantum Annealer processor with a Deep Learning architecture, increasing the timing performance with respect to first principles simulations and Deep Learning models alone, while maintaining current state-of-the-art data quality
As CERN approaches the launch of the High Luminosity Large Hadron Collider (HL-LHC) by the decade’s end, the computational demands of traditional simulations have become untenably high. Projections show millions of CPU-years required to create simulated datasets - with a substantial fraction of CPU time devoted to calorimetric simulations. This presents unique opportunities for breakthroughs in computational physics. We show how Quantumassisted Generative AI can be used for the purpose of creating synthetic, realistically scaled calorimetry dataset. The model is constructed by combining D-Wave’s Quantum Annealer processor with a Deep Learning architecture, increasing the timing performance with respect to first principles simulations and Deep Learning models alone, while maintaining current state-of-the-art data quality