arXiv subjects

Dirk Krücker

Publications and source records attributed to Dirk Krücker.

At least 19 recordsLinked to original sources

arXiv2026

An IQP Born Machine for Calorimeter Image Generation at 64 Qubits with Compiled-IQP Deployment

The challenge to scaling quantum generative models on near-term hardware is training. Variational circuit Born machines require repeated quantum sampling and are prone to barren plateaus. Instantaneous Quantum Polynomial-time (IQP) Born machines sidestep both, since their loss is built from low-order Pauli-Z correlators that admit an unbiased classical estimator, while sampling from worst-case circuits in the class is conjectured to be classically hard. We take this train-on-classical, deploy-on-quantum workflow to a real high-energy-physics generative task, learning calorimeter shower profiles at 64 qubits and running the trained model on an IBM Heron r2 superconducting processor at 67 physical qubits. Three ingredients make it work. A uniform mixture of IQP circuits (MoIQP) widens the model class at single-circuit training cost. The Pearson-Stabilized Correlation Kernel (PSCK) biases descent toward the pairwise correlations that carry the shower-development physics, which the standard heat kernel systematically compresses. An exact deferred-measurement compilation collapses the mixture into a single IQP circuit, realized on hardware as a constant-depth dynamic circuit with zero SWAP insertions on the device's native heavy-hex graph. The trained model reconstructs the correlation structure to within 0.016 of the floor imposed by the encoding itself. Raw device samples reproduce the per-cell energy spectra and the full pairwise correlation structure at Pearson r = 0.989, up to a single global amplitude compression of depolarizing origin. A Gaussian copula fitted to the same training split matches the pairwise target more accurately than the quantum model at negligible cost. The contribution is therefore the classical trainability, exact compilation, and hardware deployability of a quantum generative model at this scale, not superiority over classical surrogates.

quant-ph↗

arXiv2026

Symbolic Pauli Propagation for Gradient-Enabled Pre-Training of Quantum Circuits

Quantum Machine Learning models typically require expensive on-chip training procedures and often lack efficient gradient estimation methods. By employing Pauli propagation, it is possible to derive a symbolic representation of observables as analytic functions of a circuit's parameters. Although the number of terms in such functional representations grows rapidly with circuit depth, suitable choices of ansatz and controlled truncations on Pauli weights and frequency components yield accurate yet tractable estimators of the target observables. With the right ansatz design, this approach can be extended to system sizes beyond the reach of classical statevector simulation, enabling scalable training for larger quantum systems. This also enables a form of classical pre-training through gradient-based optimization prior to deployment on quantum hardware. The proposed approach is demonstrated on the Variational Quantum Eigensolver for obtaining the ground state of the ANNNI spin model on 32 qubits, showing that accurate results can be achieved with a scalable and computationally efficient procedure.

quant-ph↗

arXiv2025

CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation

We present the results of the "Fast Calorimeter Simulation Challenge 2022" - the CaloChallenge. We study state-of-the-art generative models on four calorimeter shower datasets of increasing dimensionality, ranging from a few hundred voxels to a few tens of thousand voxels. The 31 individual submissions span a wide range of current popular generative architectures, including Variational AutoEncoders (VAEs), Generative Adversarial Networks (GANs), Normalizing Flows, Diffusion models, and models based on Conditional Flow Matching. We compare all submissions in terms of quality of generated calorimeter showers, as well as shower generation time and model size. To assess the quality we use a broad range of different metrics including differences in 1-dimensional histograms of observables, KPD/FPD scores, AUCs of binary classifiers, and the log-posterior of a multiclass classifier. The results of the CaloChallenge provide the most complete and comprehensive survey of cutting-edge approaches to calorimeter fast simulation to date. In addition, our work provides a uniquely detailed perspective on the important problem of how to evaluate generative models. As such, the results presented here should be applicable for other domains that use generative AI and require fast and faithful generation of samples in a large phase space.

physics.ins-det↗

arXiv2024

Pay Attention To Mean Fields For Point Cloud Generation

Collider data generation with machine learning has become increasingly popular in particle physics due to the high computational cost of conventional Monte Carlo simulations, particularly for future high-luminosity colliders. We propose a generative model for point clouds that employs an attention-based aggregation while preserving a linear computational complexity with respect to the number of points. The model is trained in an adversarial setup, ensuring input permutation equivariance and invariance for the generator and critic, respectively. To stabilize known unstable adversarial training, a feature matching loss is introduced. We evaluate the performance on two different datasets. The former is the top-quark \textsc{JetNet150} dataset, where the model outperforms the current state-of-the-art GAN-based model, despite having significantly fewer parameters. The latter is dataset 2 of the CaloChallenge, which comprises point clouds with up to $30\times$ more points compared to the first dataset. The model and its corresponding code are available at \url{https://github.com/kaechb/MDMA/tree/NeurIPS}.

hep-ex↗

arXiv2024

CaloPointFlow II Generating Calorimeter Showers as Point Clouds

The simulation of calorimeter showers presents a significant computational challenge, impacting the efficiency and accuracy of particle physics experiments. While generative ML models have been effective in enhancing and accelerating the conventional physics simulation processes, their application has predominantly been constrained to fixed detector readout geometries. With CaloPointFlow we have presented one of the first models that can generate a calorimeter shower as a point cloud. This study describes CaloPointFlow II, which exhibits several significant improvements compared to its predecessor. This includes a novel dequantization technique, referred to as CDF-Dequantization, and a normalizing flow architecture, referred to as DeepSet- Flow. The new model was evaluated with the fast Calorimeter Simulation Challenge (CaloChallenge) Dataset II and III.

physics.ins-det↗

arXiv2024

A Full Quantum Generative Adversarial Network Model for High Energy Physics Simulations

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.

quant-ph↗

arXiv2024

DeepTreeGANv2: Iterative Pooling of Point Clouds

In High Energy Physics, detailed and time-consuming simulations are used for particle interactions with detectors. To bypass these simulations with a generative model, the generation of large point clouds in a short time is required, while the complex dependencies between the particles must be correctly modelled. Particle showers are inherently tree-based processes, as each particle is produced by the decay or detector interaction of a particle of the previous generation. In this work, we present a significant extension to DeepTreeGAN, featuring a critic, that is able to aggregate such point clouds iteratively in a tree-based manner. We show that this model can reproduce complex distributions, and we evaluate its performance on the public JetNet 150 dataset.

physics.data-an↗

arXiv2023

DeepTreeGAN: Fast Generation of High Dimensional Point Clouds

In High Energy Physics, detailed and time-consuming simulations are used for particle interactions with detectors. To bypass these simulations with a generative model, the generation of large point clouds in a short time is required, while the complex dependencies between the particles must be correctly modelled. Particle showers are inherently tree-based processes, as each particle is produced by the decay or detector interaction of a particle of the previous generation. In this work, we present a novel Graph Neural Network model (DeepTreeGAN) that is able to generate such point clouds in a tree-based manner. We show that this model can reproduce complex distributions, and we evaluate its performance on the public JetNet dataset.

hep-ex↗

arXiv2023

Precise Image Generation on Current Noisy Quantum Computing Devices

The Quantum Angle Generator (QAG) is a new full Quantum Machine Learning model designed to generate accurate images on current Noise Intermediate Scale (NISQ) Quantum devices. Variational quantum circuits form the core of the QAG model, and various circuit architectures are evaluated. In combination with the so-called MERA-upsampling architecture, the QAG model achieves excellent results, which are analyzed and evaluated in detail. To our knowledge, this is the first time that a quantum model has achieved such accurate results. To explore the robustness of the model to noise, an extensive quantum noise study is performed. In this paper, it is demonstrated that the model trained on a physical quantum device learns the noise characteristics of the hardware and generates outstanding results. It is verified that even a quantum hardware machine calibration change during training of up to 8% can be well tolerated. For demonstration, the model is employed in indispensable simulations in high energy physics required to measure particle energies and, ultimately, to discover unknown particles at the Large Hadron Collider at CERN.

quant-ph↗

arXiv2023

Volumetric Benchmarking of Quantum Computing Noise Models

The main challenge of quantum computing on its way to scalability is the erroneous behaviour of current devices. Understanding and predicting their impact on computations is essential to counteract these errors with methods such as quantum error mitigation. Thus, it is necessary to construct and evaluate accurate noise models. However, the evaluation of noise models does not yet follow a systematic approach, making it nearly impossible to estimate the accuracy of a model for a given application. Therefore, we developed and present a systematic approach to benchmark noise models for quantum computing applications. It compares the results of hardware experiments to predictions of noise models for a representative set of quantum circuits. We also construct a noise model and optimize its parameters with a series of training circuits. We then perform a volumetric benchmark comparing our model to other models from the literature.

quant-ph↗

arXiv2022

JetFlow: Generating Jets with Conditioned and Mass Constrained Normalising Flows

Fast data generation based on Machine Learning has become a major research topic in particle physics. This is mainly because the Monte Carlo simulation approach is computationally challenging for future colliders, which will have a significantly higher luminosity. The generation of collider data is similar to point cloud generation with complex correlations between the points. In this study, the generation of jets with up to 30 constituents with Normalising Flows using Rational Quadratic Spline coupling layers is investigated. Without conditioning on the jet mass, our Normalising Flows are unable to model all correlations in data correctly, which is evident when comparing the invariant jet mass distributions between ground truth and generated data. Using the invariant mass as a condition for the coupling transformation enhances the performance on all tracked metrics. In addition, we demonstrate how to sample the original mass distribution by interpolating the empirical cumulative distribution function. Similarly, the variable number of constituents is taken care of by introducing an additional condition on the number of constituents in the jet. Furthermore, we study the usefulness of including an additional mass constraint in the loss term. On the \texttt{JetNet} dataset, our model shows state-of-the-art performance combined with fast and stable training.

hep-ex↗

arXiv2022

Point Cloud Generation using Transformer Encoders and Normalising Flows

Data generation based on Machine Learning has become a major research topic in particle physics. This is due to the current Monte Carlo simulation approach being computationally challenging for future colliders, which will have a significantly higher luminosity. The generation of collider data is similar to point cloud generation, but arguably more difficult as there are complex correlations between the points which need to be modelled correctly. A refinement model consisting of normalising flows and transformer encoders is presented. The normalising flow output is corrected by a transformer encoder, which is adversarially trained against another transformer encoder discriminator/critic. The model reaches state-of-the-art performance while yielding a stable training.

hep-ex↗

arXiv2022

Snowmass White Paper: Quantum Computing Systems and Software for High-energy Physics Research

Quantum computing offers a new paradigm for advancing high-energy physics research by enabling novel methods for representing and reasoning about fundamental quantum mechanical phenomena. Realizing these ideals will require the development of novel computational tools for modeling and simulation, detection and classification, data analysis, and forecasting of high-energy physics (HEP) experiments. While the emerging hardware, software, and applications of quantum computing are exciting opportunities, significant gaps remain in integrating such techniques into the HEP community research programs. Here we identify both the challenges and opportunities for developing quantum computing systems and software to advance HEP discovery science. We describe opportunities for the focused development of algorithms, applications, software, hardware, and infrastructure to support both practical and theoretical applications of quantum computing to HEP problems within the next 10 years.

quant-ph↗

arXiv2021

Physics Validation of Novel Convolutional 2D Architectures for Speeding Up High Energy Physics Simulations

The precise simulation of particle transport through detectors remains a key element for the successful interpretation of high energy physics results. However, Monte Carlo based simulation is extremely demanding in terms of computing resources. This challenge motivates investigations of faster, alternative approaches for replacing the standard Monte Carlo approach. We apply Generative Adversarial Networks (GANs), a deep learning technique, to replace the calorimeter detector simulations and speeding up the simulation time by orders of magnitude. We follow a previous approach which used three-dimensional convolutional neural networks and develop new two-dimensional convolutional networks to solve the same 3D image generation problem faster. Additionally, we increased the number of parameters and the neural networks representational power, obtaining a higher accuracy. We compare our best convolutional 2D neural network architecture and evaluate it versus the previous 3D architecture and Geant4 data. Our results demonstrate a high physics accuracy and further consolidate the use of GANs for fast detector simulations.

hep-ex↗

arXiv2021

Modelling for Quantum Error Mitigation

While we expect quantum computers to surpass their classical counterparts in the future, current devices are prone to high error rates and techniques to minimise the impact of these errors are indispensable. There already exists a variety of error mitigation methods addressing this quantum noise that differ in effectiveness, and scalability. But for a more systematic and comprehensible approach we propose the introduction of modelling, in particular for representing cause-effect relations as well as for evaluating methods or combinations thereof with respect to a selection of relevant criteria.

quant-ph↗

arXiv2021

Validation of Deep Convolutional Generative Adversarial Networks for High Energy Physics Calorimeter Simulations

In particle physics the simulation of particle transport through detectors requires an enormous amount of computational resources, utilizing more than 50% of the resources of the CERN Worldwide Large Hadron Collider Grid. This challenge has motivated the investigation of different, faster approaches for replacing the standard Monte Carlo simulations. Deep Learning Generative Adversarial Networks are among the most promising alternatives. Previous studies showed that they achieve the necessary level of accuracy while decreasing the simulation time by orders of magnitudes. In this paper we present a newly developed neural network architecture which reproduces a three-dimensional problem employing 2D convolutional layers and we compare its performance with an earlier architecture consisting of 3D convolutional layers. The performance evaluation relies on direct comparison to Monte Carlo simulations, in terms of different physics quantities usually employed to quantify the detector response. We prove that our new neural network architecture reaches a higher level of accuracy with respect to the 3D convolutional GAN while reducing the necessary computational resources. Calorimeters are among the most expensive detectors in terms of simulation time. Therefore we focus our study on an electromagnetic calorimeter prototype with a regular highly granular geometry, as an example of future calorimeters.

hep-ex↗

arXiv2021

Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case

Deep learning is finding its way into high energy physics by replacing traditional Monte Carlo simulations. However, deep learning still requires an excessive amount of computational resources. A promising approach to make deep learning more efficient is to quantize the parameters of the neural networks to reduced precision. Reduced precision computing is extensively used in modern deep learning and results to lower execution inference time, smaller memory footprint and less memory bandwidth. In this paper we analyse the effects of low precision inference on a complex deep generative adversarial network model. The use case which we are addressing is calorimeter detector simulations of subatomic particle interactions in accelerator based high energy physics. We employ the novel Intel low precision optimization tool (iLoT) for quantization and compare the results to the quantized model from TensorFlow Lite. In the performance benchmark we gain a speed-up of 1.73x on Intel hardware for the quantized iLoT model compared to the initial, not quantized, model. With different physics-inspired self-developed metrics, we validate that the quantized iLoT model shows a lower loss of physical accuracy in comparison to the TensorFlow Lite model.

physics.data-an↗

arXiv2018

Direct optimisation of the discovery significance when training neural networks to search for new physics in particle colliders

We introduce two new loss functions designed to directly optimise the statistical significance of the expected number of signal events when training neural networks to classify events as signal or background in the scenario of a search for new physics at a particle collider. The loss functions are designed to directly maximise commonly used estimates of the statistical significance, $s/\sqrt{s+b}$, and the Asimov estimate, $Z_A$. We consider their use in a toy SUSY search with 30~fb$^{-1}$ of 14~TeV data collected at the LHC. In the case that the search for the SUSY model is dominated by systematic uncertainties, it is found that the loss function based on $Z_A$ can outperform the binary cross entropy in defining an optimal search region.

hep-ex↗