arXiv subjects

Tilman Plehn

Publications and source records attributed to Tilman Plehn.

At least 55 records · Page 3Linked to original sources

arXiv2025

SKATR: A Self-Supervised Summary Transformer for SKA

The Square Kilometer Array will initiate a new era of radio astronomy by allowing 3D imaging of the Universe during Cosmic Dawn and Reionization. Modern machine learning is crucial to analyse the highly structured and complex signal. However, accurate training data is expensive to simulate, and supervised learning may not generalize. We introduce a self-supervised vision transformer, SKATR, whose learned encoding can be cheaply adapted for downstream tasks on 21cm maps. Focusing on regression and generative inference of astrophysical and cosmological parameters, we demonstrate that SKATR representations are maximally informative and that SKATR generalises out-of-domain to differently-simulated, noised, and higher-resolution datasets.

astro-ph.IM↗

arXiv2025

Modern Machine Learning for LHC Physicists

Depending on the point of view, modern machine learning is either providing an unprecedented boost to the numerical methods of particle physics, or it is transforming the way we do science with vast amounts of complex data. In any case, it is crucial for young researchers to stay on top of this development and apply cutting-edge methods and tools to all LHC physics tasks. These lecture notes lead students with basic knowledge of particle physics and significant enthusiasm for machine learning to relevant applications. They start with an LHC-specific motivation and a non-standard introduction to neural networks and then cover classification, unsupervised classification, generative networks, data representations, and inverse problems. Three themes defining much of the discussion are statistically defined loss functions, uncertainties, and accuracy. To understand the applications, the notes include some aspects of theoretical LHC physics. All examples are chosen from particle physics publications of the last few years, and many of them come with corresponding tutorials.

hep-ph↗

arXiv2025

A Global View of the EDM Landscape

Permanent electric dipole moments (EDMs) are sensitive probes of the symmetry structure of elementary particles, which in turn is closely tied to the baryon asymmetry in the universe. A meaningful interpretation framework for EDM measurements has to be based on effective quantum field theory. We interpret the measurements performed to date in terms of a hadronic-scale Lagrangian, using the SFitter global analysis framework. We find that part of this Lagrangian is constrained very well, while some of the parameters suffer from too few high-precision measurements. Theory uncertainties lead to weaker model constraints, but can be controlled within the global analysis.

hep-ph↗

arXiv2025

Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN

Modern machine learning will allow for simulation-based inference from reionization-era 21cm observations at the Square Kilometre Array. Our framework combines a convolutional summary network and a conditional invertible network through a physics-inspired latent representation. It allows for an efficient and extremely fast determination of the posteriors of astrophysical and cosmological parameters, jointly with well-calibrated and on average unbiased summaries. The sensitivity to non-Gaussian information makes our method a promising alternative to the established power spectra.

astro-ph.CO↗

arXiv2025

Profile Likelihoods on ML-Steroids

Profile likelihoods, for instance, describing global SMEFT analyses at the LHC are numerically expensive to construct and evaluate. Especially profiled likelihoods are notoriously unstable and noisy. We show how modern numerical tools, similar to neural importance sampling, lead to a huge numerical improvement and allow us to evaluate the complete SFitter SMEFT likelihood in five hours on a single GPU.

hep-ph↗

arXiv2025

Staying on Top of SMEFT-Likelihood Analyses

We present a new global SMEFT analysis of LHC data in the top sector. After updating our set of measurements, we show how public ATLAS likelihoods can be incorporated into an external global analysis and how our analysis benefits from the additional information. We find that, unlike for the Higgs and electroweak sector, the SMEFT analysis of the top sector is mostly limited by the theory uncertainties. Finally, we present the first global SFitter analysis combining the top and electroweak-Higgs sectors.

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

Differentiable MadNIS-Lite

Differentiable programming opens exciting new avenues in particle physics, also affecting future event generators. These new techniques boost the performance of current and planned MadGraph implementations. Combining phase-space mappings with a set of very small learnable flow elements, MadNIS-Lite, can improve the sampling efficiency while being physically interpretable. This defines a third sampling strategy, complementing VEGAS and the full MadNIS.

hep-ph↗

arXiv2024

Jet Diffusion versus JetGPT -- Modern Networks for the LHC

We introduce two diffusion models and an autoregressive transformer for LHC physics simulations. Bayesian versions allow us to control the networks and capture training uncertainties. After illustrating their different density estimation methods for simple toy models, we discuss their advantages for Z plus jets event generation. While diffusion networks excel through their precision, the transformer scales best with the phase space dimensionality. Given the different training and evaluation speed, we expect LHC physics to benefit from dedicated use cases for normalizing flows, diffusion models, and autoregressive transformers.

hep-ph↗

arXiv2024

Constraining the Higgs Potential with Neural Simulation-based Inference for Di-Higgs Production

Determining the form of the Higgs potential is one of the most exciting challenges of modern particle physics. Higgs pair production directly probes the Higgs self-coupling and should be observed in the near future at the High-Luminosity LHC. We explore how to improve the sensitivity to physics beyond the Standard Model through per-event kinematics for di-Higgs events. In particular, we employ machine learning through simulation-based inference to estimate per-event likelihood ratios and gauge potential sensitivity gains from including this kinematic information. In terms of the Standard Model Effective Field Theory, we find that adding a limited number of observables can help to remove degeneracies in Wilson coefficient likelihoods and significantly improve the experimental sensitivity.

hep-ph↗

arXiv2024

Generative Unfolding with Distribution Mapping

Machine learning enables unbinned, highly-differential cross section measurements. A recent idea uses generative models to morph a starting simulation into the unfolded data. We show how to extend two morphing techniques, Schrödinger Bridges and Direct Diffusion, in order to ensure that the models learn the correct conditional probabilities. This brings distribution mapping to a similar level of accuracy as the state-of-the-art conditional generative unfolding methods. Numerical results are presented with a standard benchmark dataset of single jet substructure as well as for a new dataset describing a 22-dimensional phase space of Z + 2-jets.

hep-ph↗

arXiv2024

Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr), a new multi-purpose architecture for high-energy physics. L-GATr represents high-energy data in a geometric algebra over four-dimensional space-time and is equivariant under Lorentz transformations, the symmetry group of relativistic kinematics. At the same time, the architecture is a Transformer, which makes it versatile and scalable to large systems. L-GATr is first demonstrated on regression and classification tasks from particle physics. We then construct the first Lorentz-equivariant generative model: a continuous normalizing flow based on an L-GATr network, trained with Riemannian flow matching. Across our experiments, L-GATr is on par with or outperforms strong domain-specific baselines.

physics.data-an↗

arXiv2024

Precision-Machine Learning for the Matrix Element Method

The matrix element method is the LHC inference method of choice for limited statistics. We present a dedicated machine learning framework, based on efficient phase-space integration, a learned acceptance and transfer function. It is based on a choice of INN and diffusion networks, and a transformer to solve jet combinatorics. We showcase this setup for the CP-phase of the top Yukawa coupling in associated Higgs and single-top production.

hep-ph↗

arXiv2024

Kicking it Off(-shell) with Direct Diffusion

Off-shell effects in large LHC backgrounds are crucial for precision predictions and, at the same time, challenging to simulate. We present a novel method to transform high-dimensional distributions based on a diffusion neural network and use it to generate a process with off-shell kinematics from the much simpler on-shell one. Applied to a toy example of top pair production at LO we show how our method generates off-shell configurations fast and precisely, while reproducing even challenging on-shell features.

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↗

arXiv2024

The MadNIS Reloaded

In pursuit of precise and fast theory predictions for the LHC, we present an implementation of the MadNIS method in the MadGraph event generator. A series of improvements in MadNIS further enhance its efficiency and speed. We validate this implementation for realistic partonic processes and find significant gains from using modern machine learning in event generators.

hep-ph↗