Humberto Reyes-González

The LHC physics programme involves a vast amount of Monte Carlo event simulation. This paper reviews current efforts towards sharing the generated events as Open Data. Open Event Generation helps reduce duplication of effort and resource consumption, and benefits the whole High Energy Physics community. We give examples of use cases and user experiences, discuss financial and environmental savings, and suggest future directions.

Generative models are increasingly central to scientific workflows, yet their systematic use and interpretation require a proper understanding of their limitations through rigorous validation. Classic approaches struggle with scalability, statistical power, or interpretability when applied to high-dimensional data, making it difficult to certify the reliability of these models in realistic, high-dimensional scientific settings. Here, we propose the use of the New Physics Learning Machine (NPLM), a learning-based approach to goodness-of-fit testing inspired by the Neyman–Pearson construction, to test generative networks trained on high-dimensional scientific data. We demonstrate the performance of NPLM for validation in two benchmark cases: generative models trained on mixtures of Gaussian models with increasing dimensionality, and a public end-to-end model developed to generate high-energy physics collision events. We show that NPLM can serve as a powerful validation method while also providing a means to diagnose sub-optimally modeled regions of the data.

Identifying the origin of high-energy hadronic jets (jet tagging) has been a critical benchmark problem for machine learning in particle physics. Jets are ubiquitous at colliders and are complex objects that serve as prototypical examples of collections of particles to be categorized. Over the last decade, machine learning-based classifiers have replaced classical observables as the state of the art in jet tagging. Increasingly complex machine learning models are leading to increasingly more effective tagger performance. Our goal is to address the question of convergence—are we getting close to the fundamental limit on jet tagging or is there still potential for computational, statistical, and physical insights for further improvements? We address this question using state-of-the-art generative models to create a realistic, synthetic dataset with a known jet tagging optimum. Various state-of-the-art taggers are deployed on this dataset, showing that there is a significant gap between their performance and the optimum. Our dataset and software are made public to provide a benchmark task for future developments in jet tagging and other areas of particle physics.

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 one-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. Report Numbers : HEPHY-ML-24-05, FERMILAB-PUB-24-0728-CMS, TTK-24-43.

Foundation models are deep learning models pre-trained on large amounts of data which are capable of generalizing to multiple datasets and/or downstream tasks. This work demonstrates how data collected by the CMS experiment at the Large Hadron Collider can be useful in pre-training foundation models for HEP. Specifically, we introduce the AspenOpenJets (AOJs) dataset, consisting of approximately 178 M high p T jets derived from CMS 2016 Open Data. We show how pre-training the OmniJet-α foundation model on AOJs improves performance on generative tasks with significant domain shift: generating boosted top and QCD jets from the simulated JetClass dataset. In addition to demonstrating the power of pre-training of a jet-based foundation model on actual proton–proton collision data, we provide the ML-ready derived AOJs dataset for further public use.

With the increasing usage of machine-learning in high-energy physics analyses, the publication of the trained models in a reusable form has become a crucial question for analysis preservation and reuse. The complexity of these models creates practical issues for both reporting them accurately and for ensuring the stability of their behaviours in different environments and over extended timescales. In this note we discuss the current state of affairs, highlighting specific practical issues and focusing on the most promising technical and strategic approaches to ensure trustworthy analysis-preservation. This material originated from discussions in the LHC Reinterpretation Forum and the 2023 PhysTeV workshop at Les Houches.

We propose the NFLikelihood, an unsupervised version, based on Normalizing Flows, of the DNNLikelihood proposed in [Eur. Phys. J. C 80, 664 (2020)]. We show, through realistic examples, how Autoregressive Flows, based on affine and rational quadratic spline bijectors, are able to learn complicated high-dimensional Likelihoods arising in High Energy Physics (HEP) analyses. We focus on a toy LHC analysis example already considered in the literature and on two Effective Field Theory fits of flavor and electroweak observables, whose samples have been obtained through the HEPFit code. We discuss advantages and disadvantages of the unsupervised approach with respect to the supervised one and discuss a possible interplay between the two.

Normalizing flows have emerged as a powerful brand of generative models, as they not only allow for efficient sampling of complicated target distributions but also deliver density estimation by construction. We propose here an in-depth comparison of coupling and autoregressive flows, both based on symmetric (affine) and non-symmetric (rational quadratic spline) bijectors, considering four different architectures: real-valued non-Volume preserving (RealNVP), masked autoregressive flow (MAF), coupling rational quadratic spline (C-RQS), and autoregressive rational quadratic spline (A-RQS). We focus on a set of multimodal target distributions of increasing dimensionality ranging from 4 to 400. The performances were compared by means of different test statistics for two-sample tests, built from known distance measures: the sliced Wasserstein distance, the dimension-averaged one-dimensional Kolmogorov–Smirnov test, and the Frobenius norm of the difference between correlation matrices. Furthermore, we included estimations of the variance of both the metrics and the trained models. Our results indicate that the A-RQS algorithm stands out both in terms of accuracy and training speed. Nonetheless, all the algorithms are generally able, without too much fine-tuning, to learn complicated distributions with limited training data and in a reasonable time of the order of hours on a Tesla A40 GPU. The only exception is the C-RQS, which takes significantly longer to train, does not always provide good accuracy, and becomes unstable for large dimensionalities. All algorithms were implemented using TensorFlow2 and TensorFlow Probability and have been made available on GitHub.

To gain a comprehensive view of what the LHC tells us about physics beyond the Standard Model (BSM), it is crucial that different BSM-sensitive analyses can be combined. But in general search-analyses are not statistically orthogonal, so performing comprehensive combinations requires knowledge of the extent to which the same events co-populate multiple analyses’ signal regions. We present a novel, stochastic method to determine this degree of overlap, and a graph algorithm to efficiently find the combination of signal regions with no mutual overlap that optimises expected upper limits on BSM-model cross-sections. The gain in exclusion power relative to single-analysis limits is demonstrated with models with varying degrees of complexity, ranging from simplified models to a 19-dimensional supersymmetric model.

Most SUSY searches at the LHC are optimised for the MSSM, where gauginos are Majorana particles. By introducing Dirac gauginos, we obtain an enriched phenomenology, from which considerable differences in the LHC signatures and limits are expected as compared to the MSSM. Concretely, in the minimal Dirac gaugino model (MDGSSM) we have six neutralino and three chargino states. Moreover, production cross sections are enhanced for gluinos, while for squarks they are suppressed. In this contribution we show concrete results for the current LHC limits on gluinos and squarks in this model.