Publications

Order by: publication date number of citations

• Deep Set Auto Encoders for Anomaly Detection in Particle Physics

  Bryan Ostdiek

  SciPost Phys. 12, 045 (2022) · published 31 January 2022 | Toggle abstract · pdf

  There is an increased interest in model agnostic search strategies for physics beyond the standard model at the Large Hadron Collider. We introduce a Deep Set Variational Autoencoder and present results on the Dark Machines Anomaly Score Challenge. We find that the method attains the best anomaly detection ability when there is no decoding step for the network, and the anomaly score is based solely on the representation within the encoded latent space. This method was one of the top-performing models in the Dark Machines Challenge, both for the open data sets as well as the blinded data sets.

  26 citations

• Measuring QCD Splittings with Invertible Networks

  Sebastian Bieringer, Anja Butter, Theo Heimel, Stefan Höche, Ullrich Köthe, Tilman Plehn, Stefan T. Radev

  SciPost Phys. 10, 126 (2021) · published 2 June 2021 | Toggle abstract · pdf

  QCD splittings are among the most fundamental theory concepts at the LHC. We show how they can be studied systematically with the help of invertible neural networks. These networks work with sub-jet information to extract fundamental parameters from jet samples. Our approach expands the LEP measurements of QCD Casimirs to a systematic test of QCD properties based on low-level jet observables. Starting with an toy example we study the effect of the full shower, hadronization, and detector effects in detail.

  26 citations

• Understanding Event-Generation Networks via Uncertainties

  Marco Bellagente, Manuel Haußmann, Michel Luchmann, Tilman Plehn

  SciPost Phys. 13, 003 (2022) · published 21 July 2022 | Toggle abstract · pdf

  Following the growing success of generative neural networks in LHC simulations, the crucial question is how to control the networks and assign uncertainties to their event output. We show how Bayesian normalizing flow or invertible networks capture uncertainties from the training and turn them into an uncertainty on the event weight. Fundamentally, the interplay between density and uncertainty estimates indicates that these networks learn functions in analogy to parameter fits rather than binned event counts.

  26 citations

• Strongly Interacting Light Dark Matter

  Sebastian Bruggisser, Francesco Riva, Alfredo Urbano

  SciPost Phys. 3, 017 (2017) · published 2 September 2017 | Toggle abstract · pdf

  In the presence of approximate global symmetries that forbid relevant interactions, strongly coupled light Dark Matter (DM) can appear weakly coupled at small energy and generate a sizable relic abundance. Fundamental principles like unitarity restrict these symmetries to a small class, where the leading interactions are captured by effective operators up to dimension-8. Chiral symmetry, spontaneously broken global symmetries and non-linearly realized supersymmetry are examples of this. Their DM candidates (composite fermions, pseudo Nambu-Goldstone Bosons and Goldstini) are interesting targets for LHC missing-energy searches.

  25 citations

• How to GAN Event Unweighting

  Mathias Backes, Anja Butter, Tilman Plehn, Ramon Winterhalder

  SciPost Phys. 10, 089 (2021) · published 23 April 2021 | Toggle abstract · pdf

  Event generation with neural networks has seen significant progress recently. The big open question is still how such new methods will accelerate LHC simulations to the level required by upcoming LHC runs. We target a known bottleneck of standard simulations and show how their unweighting procedure can be improved by generative networks. This can, potentially, lead to a very significant gain in simulation speed.

  25 citations

• Event Generation and Density Estimation with Surjective Normalizing Flows

  Rob Verheyen

  SciPost Phys. 13, 047 (2022) · published 2 September 2022 | Toggle abstract · pdf

  Normalizing flows are a class of generative models that enable exact likelihood evaluation. While these models have already found various applications in particle physics, normalizing flows are not flexible enough to model many of the peripheral features of collision events. Using the framework of Nielsen et al. (2020), we introduce several surjective and stochastic transform layers to a baseline normalizing flow to improve modelling of permutation symmetry, varying dimensionality and discrete features, which are all commonly encountered in particle physics events. We assess their efficacy in the context of the generation of a matrix element-level process, and in the context of anomaly detection in detector-level LHC events.

  24 citations

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

  Alexander Shmakov, Michael James Fenton, Ta-Wei Ho, Shih-Chieh Hsu, Daniel Whiteson, Pierre Baldi

  SciPost Phys. 12, 178 (2022) · published 30 May 2022 | Toggle abstract · pdf

  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 avaiable at https://github.com/Alexanders101/SPANet

  24 citations

• On-shell effective theory for higher-spin dark matter

  Adam Falkowski, Giulia Isabella, Camila S. Machado

  SciPost Phys. 10, 101 (2021) · published 6 May 2021 | Toggle abstract · pdf

  We apply the on-shell amplitude techniques in the domain of dark matter. Without evoking fields and Lagrangians, an effective theory for a massive spin-$S$ particle is defined in terms of on-shell amplitudes, which are written down using the massive spinor formalism. This procedure greatly simplifies the study of theories with a higher-spin dark matter particle. In particular, it provides an efficient way to calculate the rates of processes controlling dark matter production, and offers better physical insight into how different processes depend on the relevant scales in the theory. We demonstrate the applicability of these methods by exploring two scenarios where higher-spin DM is produced via the freeze-in mechanism. One scenario is minimal, involving only universal gravitational interactions, and is compatible with dark matter masses in a very broad range from sub-TeV to the GUT scale. The other scenario involves direct coupling of higher-spin DM to the Standard Model via the Higgs intermediary, and leads to a rich phenomenology, including dark matter decay signatures.

  24 citations

• Anomalous dimensions of potential top-partners

  Diogo Buarque Franzosi, Gabriele Ferretti

  SciPost Phys. 7, 027 (2019) · published 4 September 2019 | Toggle abstract · pdf

  We discuss anomalous dimensions of top-partner candidates in theories of Partial Compositeness. First, we revisit, confirm and extend the computation by DeGrand and Shamir of anomalous dimensions of fermionic trilinears. We present general results applicable to all matter representations and to composite operators of any allowed spin. We then ask the question of whether it is reasonable to expect some models to have composite operators of sufficiently large anomalous dimension to serve as top-partners. While this question can be answered conclusively only by lattice gauge theory, within perturbation theory we find that such values could well occur for some specific models. In the Appendix we collect a number of practical group theory results for fourth-order invariants of general interest in gauge theories with many irreducible representations of fermions.

  24 citations

• Accelerating Monte Carlo event generation -- rejection sampling using neural network event-weight estimates

  Katharina Danziger, Timo Janßen, Steffen Schumann, Frank Siegert

  SciPost Phys. 12, 164 (2022) · published 18 May 2022 | Toggle abstract · pdf

  The generation of unit-weight events for complex scattering processes presents a severe challenge to modern Monte Carlo event generators. Even when using sophisticated phase-space sampling techniques adapted to the underlying transition matrix elements, the efficiency for generating unit-weight events from weighted samples can become a limiting factor in practical applications. Here we present a novel two-staged unweighting procedure that makes use of a neural-network surrogate for the full event weight. The algorithm can significantly accelerate the unweighting process, while it still guarantees unbiased sampling from the correct target distribution. We apply, validate and benchmark the new approach in high-multiplicity LHC production processes, including $Z/W$+4 jets and $t\bar{t}$+3 jets, where we find speed-up factors up to ten.

  23 citations