arXiv subjects

Luigi Favaro

Publications and source records attributed to Luigi Favaro.

16 recordsLinked to original sources

arXiv2026

Virtues and Vices of Equivariant Transformers

We study for the first time the benefit of Lorentz-equivariant transformers for large-size jet tagging and flavor tagging. To control their computing demands, we optimize all implementations for inference cost metrics. In our scaling studies, we find that Lorentz-equivariant networks outperform standard transformers, provided geometric features are relevant. This holds true in an idealized world as well as for limited resources. The conditional gain from Lorentz equivariance provides interesting input to the development of foundation models for LHC data.

hep-ph↗

arXiv2026

On the Codesign of Scientific Experiments and Industrial Systems

The optimization of large experiments in fundamental science, such as detectors for subnuclear physics at particle colliders, shares with the optimization of complex systems for industrial or societal applications the common issue of addressing the inter-relation between parameters describing the hardware used in data production and parameters used to analyse those data. While in many cases this coupling can be ignored -- when the problem can be successfully factored into simpler sub-tasks and the latter addressed serially -- there are situations in which that approach fails to converge to the absolute maximum of expected performance, as it results in a mis-alignment of the optimized hardware and software solutions. In this work we consider a few use cases of interest in fundamental science collected primarily from particle physics and related areas, and a pot-pourri of industrial and societal applications where the matter is similarly of relevance. We discuss the emergence of strong hardware-software coupling in some of those systems, as well as co-design procedures that may be deployed to identify the global maximum of their relevant utility functions. We observe how numerous opportunities exist to advance methods and tools for hardware-software co-design optimization, bridging fundamental science and industry through application- and challenge-driven projects, and shaping the future of scientific experiments and industrial systems.

physics.ins-det↗

arXiv2026

A universal vision transformer for fast calorimeter simulations

The high-dimensional complex nature of detectors makes fast calorimeter simulations a prime application for modern generative machine learning. Vision transformers (ViTs) can emulate the Geant4 response with unmatched accuracy and are not limited to regular geometries. Starting from the CaloDREAM architecture, we demonstrate the robustness and scalability of ViTs on regular and irregular geometries, and multiple detectors. Our results show that ViTs generate electromagnetic and hadronic showers with minimal deviations from Geant4 in multiple evaluation metrics, while maintaining the generation time in the $\mathcal{O}(10-100)$ ms on a single GPU. Furthermore, we show that pretraining on a large dataset and fine-tuning on the target geometry leads to reduced training costs and higher data efficiency, or altogether improves the fidelity of generated showers.

hep-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↗

arXiv2025

Lorentz-Equivariance without Limitations

Lorentz Local Canonicalization (LLoCa) ensures exact Lorentz-equivariance for arbitrary neural networks with minimal computational overhead. For the LHC, it equivariantly predicts local reference frames for each particle and propagates any-order tensorial information between them. We apply it to graph networks and transformers. We showcase its cutting-edge performance on amplitude regression, end-to-end event generation, and jet tagging. For jet tagging, we introduce a large top tagging dataset to benchmark LLoCa versions of a range of established benchmark architectures and highlight the importance of symmetry breaking.

hep-ph↗

arXiv2025

Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant

Lorentz-equivariant neural networks are becoming the leading architectures for high-energy physics. Current implementations rely on specialized layers, limiting architectural choices. We introduce Lorentz Local Canonicalization (LLoCa), a general framework that renders any backbone network exactly Lorentz-equivariant. Using equivariantly predicted local reference frames, we construct LLoCa-transformers and graph networks. We adapt a recent approach for geometric message passing to the non-compact Lorentz group, allowing propagation of space-time tensorial features. Data augmentation emerges from LLoCa as a special choice of reference frame. Our models achieve competitive and state-of-the-art accuracy on relevant particle physics tasks, while being $4\times$ faster and using $10\times$ fewer FLOPs.

stat.ML↗

arXiv2025

Fast, accurate, and precise detector simulation with vision transformers

The speed and fidelity of detector simulations in particle physics pose compelling questions about LHC analysis and future colliders. The sparse high-dimensional data, combined with the required precision, provide a challenging task for modern generative networks. We present a comparison between solutions with different trade-offs, including accurate Conditional Flow Matching and faster coupling-based Normalising Flows. Vision Transformers allows us to emulate the energy deposition from detailed Geant4 simulations. We evaluate the networks using high-level observables, neural network classifiers, and sampling timings, showing minimum deviations from Geant4 while achieving faster generation. We use the CaloChallenge benchmark datasets for reproducibility and further development.

hep-ph↗

arXiv2025

Accurate Surrogate Amplitudes with Calibrated Uncertainties

Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activation functions are systematically tested with Kolmogorov-Arnold Networks. Then, we train neural surrogates to simultaneously predict the target amplitude and an uncertainty for the prediction. We disentangle systematic uncertainties, learned by a well-defined likelihood loss, from statistical uncertainties, which require the introduction of Bayesian neural networks or repulsive ensembles. We test the coverage of the learned uncertainties using pull distributions to quantify the calibration of cutting-edge neural surrogates.

hep-ph↗

arXiv2025

Towards Precise Simulations and Inference for the Neutron EDM

Precision measurements of neutron properties, like its permanent electric dipole moment, rely on understanding complex experimental setups in detail. We show how the properties of stored and transported ultracold neutron ensembles can be simulated reliably. In a second step, we illustrate how they can be used for simulation-based inference of the parameters associated with underlying physics processes such as neutron capture or beta decay. Our proof of principle for simulation-based inference confronts a longstanding challenge with ultracold neutrons: low measurement statistics coupled with a complex apparatus.

nucl-th↗

arXiv2025

How to Unfold Top Decays

Using unfolded top-quark decay data we can measure the top quark mass, as well as search for unexpected kinematic effects. We present a new generative unfolding method for the two tasks and show how they both benefit from unbinned, high-dimensional unfolding. Unlike weight-based or iterative generative methods we include a targeted unbiasing with respect to the training data. This shows significant advantages over standard, iterative methods, in terms of applicability, flexibility and accuracy.

hep-ph↗

arXiv2025

Semi-visible jets, energy-based models, and self-supervision

We present DarkCLR, a novel framework for detecting semi-visible jets at the LHC. DarkCLR uses a self-supervised contrastive-learning approach to create observables that are approximately invariant under relevant transformations. We use background-enhanced data to create a sensitive representation and evaluate the representations using a CLR-inspired anomaly score and a normalized autoencoder as density estimators. Our results show a remarkable sensitivity for a wide range of semi-visible jets and are more robust than a supervised classifier trained on a specific signal.

hep-ph↗

arXiv2025

Normalizing Flows for High-Dimensional Detector Simulations

Whenever invertible generative networks are needed for LHC physics, normalizing flows show excellent performance. In this work, we investigate their performance for fast calorimeter shower simulations with increasing phase space dimension. We use fast and expressive coupling spline transformations applied to the CaloChallenge datasets. In addition to the base flow architecture we also employ a VAE to compress the dimensionality and train a generative network in the latent space. We evaluate our networks on several metrics, including high-level features, classifiers, and generation timing. Our findings demonstrate that invertible neural networks have competitive performance when compared to autoregressive flows, while being substantially faster during generation.

hep-ph↗

arXiv2024

CaloDREAM -- Detector Response Emulation via Attentive flow Matching

Detector simulations are an exciting application of modern generative networks. Their sparse high-dimensional data combined with the required precision poses a serious challenge. We show how combining Conditional Flow Matching with transformer elements allows us to simulate the detector phase space reliably. Namely, we use an autoregressive transformer to simulate the energy of each layer, and a vision transformer for the high-dimensional voxel distributions. We show how dimension reduction via latent diffusion allows us to train more efficiently and how diffusion networks can be evaluated faster with bespoke solvers. We showcase our framework, CaloDREAM, on datasets 2 and 3 of the CaloChallenge.

hep-ph↗

arXiv2024

Anomalies, Representations, and Self-Supervision

We develop a self-supervised method for density-based anomaly detection using contrastive learning, and test it using event-level anomaly data from CMS ADC2021. The AnomalyCLR technique is data-driven and uses augmentations of the background data to mimic non-Standard-Model events in a model-agnostic way. It uses a permutation-invariant Transformer Encoder architecture to map the objects measured in a collider event to the representation space, where the data augmentations define a representation space which is sensitive to potential anomalous features. An AutoEncoder trained on background representations then computes anomaly scores for a variety of signals in the representation space. With AnomalyCLR we find significant improvements on performance metrics for all signals when compared to the raw data baseline.

hep-ph↗

arXiv2023

How to Understand Limitations of Generative Networks

Well-trained classifiers and their complete weight distributions provide us with a well-motivated and practicable method to test generative networks in particle physics. We illustrate their benefits for distribution-shifted jets, calorimeter showers, and reconstruction-level events. In all cases, the classifier weights make for a powerful test of the generative network, identify potential problems in the density estimation, relate them to the underlying physics, and tie in with a comprehensive precision and uncertainty treatment for generative networks.

hep-ph↗

arXiv2023

A Normalized Autoencoder for LHC Triggers

Autoencoders are an effective analysis tool for the LHC, as they represent one of its main goal of finding physics beyond the Standard Model. The key challenge is that out-of-distribution anomaly searches based on the compressibility of features do not apply to the LHC, while existing density-based searches lack performance. We present the first autoencoder which identifies anomalous jets symmetrically in the directions of higher and lower complexity. The normalized autoencoder combines a standard bottleneck architecture with a well-defined probabilistic description. It works better than all available autoencoders for top vs QCD jets and reliably identifies different dark-jet signals.

hep-ph↗