Engineering Papers⌕ Search

Engineering topics

Whiteson, Daniel

Publications and source records attributed to Whiteson, Daniel.

At least 37 records · Page 2

Resolving extreme jet substructure

We study the effectiveness of theoretically-motivated high-level jet observables in the extreme context of jets with a large number of hard sub-jets (up to N = 8). Previous studies indicate that high-level observables are powerful, interpretable tools to probe jet substructure for N ≤ 3 hard sub-jets, but that deep neural networks trained on low-level jet constituents match or slightly exceed their performance. We extend this work for up to N = 8 hard sub-jets, using deep particle-flow networks (PFNs) and Transformer based networks to estimate a loose upper bound on the classification performance. A fully-connected neural network operating on a standard set of high-level jet observables, 135 N-subjetiness observables and jet mass, reach classification accuracy of 86.90%, but fall short of the PFN and Transformer models, which reach classification accuracies of 89.19% and 91.27% respectively, suggesting that the constituent networks utilize information not captured by the set of high-level observables. We then identify additional high-level observables which are able to narrow this gap, and utilize LASSO regularization for feature selection to identify and rank the most relevant observables and provide further insights into the learning strategies used by the constituent-based neural networks. The final model contains only 31 high-level observables and is able to match the performance of the PFN and approximate the performance of the Transformer model to within 2%.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

SPANet: Generalized permutationless set assignment for particle physics using symmetry preserving attention

The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics. Collisions typically produce variable-size sets of observed particles which have inherent ambiguities complicating the assignment of observed particles to the decay products of the heavy particles. Current strategies for tackling these challenges in the physics community ignore the physical symmetries of the decay products and consider all possible assignment permutations and do not scale to complex configurations. Attention based deep learning methods for sequence modelling have achieved state-of-the-art performance in natural language processing, but they lack built-in mechanisms to deal with the unique symmetries found in physical set-assignment problems. We introduce a novel method for constructing symmetry-preserving attention networks which reflect the problem's natural invariances to efficiently find assignments without evaluating all permutations. This general approach is applicable to arbitrarily complex configurations and significantly outperforms current methods, improving reconstruction efficiency between 19% - 35% on typical benchmark problems while decreasing inference time by two to five orders of magnitude on the most complex events, making many important and previously intractable cases tractable. A full code repository containing a general library, the specific configuration used, and a complete dataset release, are available at https://github.com/Alexanders101/SPANet

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Learning to simulate high energy particle collisions from unlabeled data

In many scientific fields which rely on statistical inference, simulations are often used to map from theoretical models to experimental data, allowing scientists to test model predictions against experimental results. Experimental data is often reconstructed from indirect measurements causing the aggregate transformation from theoretical models to experimental data to be poorly-described analytically. Instead, numerical simulations are used at great computational cost. We introduce Optimal-Transport-based Unfolding and Simulation (OTUS), a fast simulator based on unsupervised machine-learning that is capable of predicting experimental data from theoretical models. Without the aid of current simulation information, OTUS trains a probabilistic autoencoder to transform directly between theoretical models and experimental data. Identifying the probabilistic autoencoder’s latent space with the space of theoretical models causes the decoder network to become a fast, predictive simulator with the potential to replace current, computationally-costly simulators. Here, we provide proof-of-principle results on two particle physics examples, Z-boson and top-quark decays, but stress that OTUS can be widely applied to other fields.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Efficient sampling of constrained high-dimensional theoretical spaces with machine learning

Abstract Models of physics beyond the Standard Model often contain a large number of parameters. These form a high-dimensional space that is computationally intractable to fully explore. Experimental results project onto a subspace of parameters that are consistent with those observations, but mapping these constraints to the underlying parameters is also typically intractable. Instead, physicists often resort to scanning small subsets of the full parameter space and testing for experimental consistency. We propose an alternative approach that uses generative models to significantly improve the computational efficiency of sampling high-dimensional parameter spaces. To demonstrate this, we sample the constrained and phenomenological Minimal Supersymmetric Standard Models subject to the requirement that the sampled points are consistent with the measured Higgs boson mass. Our method achieves orders of magnitude improvements in sampling efficiency compared to a brute force search.

Hollingsworth, Jacob↗

Learning to identify electrons

In this report we investigate whether state-of-the-art classification features commonly used to distinguish electrons from jet backgrounds in collider experiments are overlooking valuable information. A deep convolutional neural network analysis of electromagnetic and hadronic calorimeter deposits is compared to the performance of typical features, revealing a ≈ 5% gap which indicates that these lower-level data do contain untapped classification power. To reveal the nature of this unused information, we use a recently developed technique to map the deep network into a space of physically interpretable observables. We identify two simple calorimeter observables which are not typically used for electron identification, but which mimic the decisions of the convolutional network and nearly close the performance gap.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

The motivation and status of two-body resonance decays after the LHC Run 2 and beyond

Searching for two-body resonance decays is a central component of the high energy physics energy frontier research program. While many of the possibilities are covered when the two bodies are Standard Model (SM) particles, there are still significant gaps. If one or both of the bodies are themselves non-SM particles, there is very little coverage from existing searches. We review the status of two-body searches and motivate the need to search for the missing combinations. It is likely that the search program of the future will be able to cover all possibilities with a combination of dedicated and model agnostic search approaches.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

The Unexplored Landscape of Two-body Resonances

We propose a strategy for searching for theoretically-unanticipated new physics which avoids a large trials factor by focusing on experimental strengths. Searches for resonances decaying into pairs of visible particles are experimentally very powerful due to the localized mass peaks and have a rich history of discovery. Yet, due to a focus on subsets of theoretically motivated models, the landscape of such resonances is far from thoroughly explored. We survey the existing set of searches, identify untapped experimental opportunities and discuss the theoretical constraints on models which would generate such resonances.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Where are the Fermi lines coming from?

We estimate the spatial locations of sources of the the observed features in the Fermi-LAT photon spectrum at E{sub γ} = 110 and E{sub γ} = 130 GeV. We determine whether they are consistent with emission from a single source, as would be expected in their interpretation as γγ and γZ lines from dark matter annhiliation, as well as whether they are consistent with a dark matter halo positioned at the center of the galaxy. We take advantage of the per-photon measured incident angle in reconstructing the line features. In addition, we use a data-driven background model rather than making the assumption of a feature-less background. We localize the sources of the features at 110 and 130 GeV. Assuming an Einasto (NFW) density model we find the 130 GeV line to be offset from the Galactic center by 285 (280) pc, the 110 GeV line by 60 (30) pc with a large relative separation of 220 (240) pc. However, we find this displacement of each source from the Galactic center, as well as their relative displacement to be statistically consistent with a single Einasto or NFW dark matter halo at the center of the galaxy.

79 ASTRONOMY AND ASTROPHYSICS↗

Disentangling instrumental features of the 130 GeV Fermi line

We study the instrumental features of photons from the peak observed at E{sub γ} = 130 GeV in the spectrum of Fermi-LAT data. We use the sPlots algorithm to reconstruct — seperately for the photons in the peak and for background photons — the distributions of quantities such as incident angles, the recorded time, features of the spacecraft position, the zenith angles, the conversion type and details of the energy and direction reconstruction. The presence of a striking feature or cluster in such a variable would suggest an instrumental cause for the peak. In the publically available data, we find several suggestive features which may inform further studies by instrumental experts, though the size of the signal sample is too small to draw statistically significant conclusions.

79 ASTRONOMY AND ASTROPHYSICS↗