Publications

Order by: publication date number of citations

• Targeting multi-loop integrals with neural networks

  Ramon Winterhalder, Vitaly Magerya, Emilio Villa, Stephen P. Jones, Matthias Kerner, Anja Butter, Gudrun Heinrich, Tilman Plehn

  SciPost Phys. 12, 129 (2022) · published 13 April 2022 | Toggle abstract · pdf

  Numerical evaluations of Feynman integrals often proceed via a deformation of the integration contour into the complex plane. While valid contours are easy to construct, the numerical precision for a multi-loop integral can depend critically on the chosen contour. We present methods to optimize this contour using a combination of optimized, global complex shifts and a normalizing flow. They can lead to a significant gain in precision.

  18 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

  18 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.

  17 citations

• Machine learning and LHC event generation

  Anja Butter, Tilman Plehn, Steffen Schumann, Simon Badger, Sascha Caron, Kyle Cranmer, Francesco Armando Di Bello, Etienne Dreyer, Stefano Forte, Sanmay Ganguly, Dorival Gonçalves, Eilam Gross, Theo Heimel, Gudrun Heinrich, Lukas Heinrich, Alexander Held, Stefan Höche, Jessica N. Howard, Philip Ilten, Joshua Isaacson, Timo Janßen, Stephen Jones, Marumi Kado, Michael Kagan, Gregor Kasieczka, Felix Kling, Sabine Kraml, Claudius Krause, Frank Krauss, Kevin Kröninger, Rahool Kumar Barman, Michel Luchmann, Vitaly Magerya, Daniel Maitre, Bogdan Malaescu, Fabio Maltoni, Till Martini, Olivier Mattelaer, Benjamin Nachman, Sebastian Pitz, Juan Rojo, Matthew Schwartz, David Shih, Frank Siegert, Roy Stegeman, Bob Stienen, Jesse Thaler, Rob Verheyen, Daniel Whiteson, Ramon Winterhalder, Jure Zupan

  SciPost Phys. 14, 079 (2023) · published 21 April 2023 | Toggle abstract · pdf

  First-principle simulations are at the heart of the high-energy physics research program. They link the vast data output of multi-purpose detectors with fundamental theory predictions and interpretation. This review illustrates a wide range of applications of modern machine learning to event generation and simulation-based inference, including conceptional developments driven by the specific requirements of particle physics. New ideas and tools developed at the interface of particle physics and machine learning will improve the speed and precision of forward simulations, handle the complexity of collision data, and enhance inference as an inverse simulation problem.

  17 citations

• Froissart bound for/from CFT Mellin amplitudes

  Parthiv Haldar, Aninda Sinha

  SciPost Phys. 8, 095 (2020) · published 30 June 2020 | Toggle abstract · pdf

  We derive bounds analogous to the Froissart bound for the absorptive part of CFT$_d$ Mellin amplitudes. Invoking the AdS/CFT correspondence, these amplitudes correspond to scattering in AdS$_{d+1}$. We can take a flat space limit of the corresponding bound. We find the standard Froissart-Martin bound, including the coefficient in front for $d+1=4$ being $\pi/\mu^2$, $\mu$ being the mass of the lightest exchange. For $d>4$, the form is different. We show that while for $CFT_{d\leq 6}$, the number of subtractions needed to write a dispersion relation for the Mellin amplitude is equal to 2, for $CFT_{d>6}$ the number of subtractions needed is greater than 2 and goes to infinity as $d$ goes to infinity.

  17 citations

• Gravitational waves from an axion-dark photon system: A lattice study

  Wolfram Ratzinger, Pedro Schwaller, Ben A. Stefanek

  SciPost Phys. 11, 001 (2021) · published 6 July 2021 | Toggle abstract · pdf

  In this work, we present a lattice study of an axion - dark photon system in the early Universe and show that the stochastic gravitational wave (GW) background produced by this system may be probed by future GW experiments across a vast range of frequencies. The numerical simulation on the lattice allows us to take into account non-linear backreaction effects and enables us to accurately predict the final relic abundance of the axion or axion-like particle (ALP) as well as its inhomogeneities, and gives a more precise prediction of the GW spectrum. Importantly, we find that the GW spectrum has more power at high momenta due to $2\rightarrow1$ processes. Furthermore, we find the degree of polarization of the peak of the GW spectrum depends on the ALP-dark photon coupling and that the polarization can be washed out or even flipped for large values thereof. In line with recent results in the literature, we find the ALP relic abundance may be suppressed by two orders of magnitude and discuss possible extensions of the model that expand the viable parameter space. Finally, we discuss the possibility to probe ultralight ALP dark matter via spectral distortions of the CMB.

  17 citations

• Testing new physics models with global comparisons to collider measurements: the Contur toolkit

  A. Buckley, J. M. Butterworth, L. Corpe, M. Habedank, D. Huang, D. Yallup, M. Altakach, G. Bassman, I. Lagwankar, J. Rocamonde, H. Saunders, B. Waugh, G. Zilgalvis

  SciPost Phys. Core 4, 013 (2021) · published 20 May 2021 | Toggle abstract · pdf

  Measurements at particle collider experiments, even if primarily aimed at understanding Standard Model processes, can have a high degree of model independence, and implicitly contain information about potential contributions from physics beyond the Standard Model. The Contur package allows users to benefit from the hundreds of measurements preserved in the Rivet library to test new models against the bank of LHC measurements to date. This method has proven to be very effective in several recent publications from the Contur team, but ultimately, for this approach to be successful, the authors believe that the Contur tool needs to be accessible to the wider high energy physics community. As such, this manual accompanies the first user-facing version: Contur v2. It describes the design choices that have been made, as well as detailing pitfalls and common issues to avoid. The authors hope that with the help of this documentation, external groups will be able to run their own Contur studies, for example when proposing a new model, or pitching a new search.

  16 citations

• How to GAN event subtraction

  Anja Butter, Tilman Plehn, Ramon Winterhalder

  SciPost Phys. Core 3, 009 (2020) · published 5 November 2020 | Toggle abstract · pdf

  Subtracting event samples is a common task in LHC simulation and analysis, and standard solutions tend to be inefficient. We employ generative adversarial networks to produce new event samples with a phase space distribution corresponding to added or subtracted input samples. We first illustrate for a toy example how such a network beats the statistical limitations of the training data. We then show how such a network can be used to subtract background events or to include non-local collinear subtraction events at the level of unweighted 4-vector events.

  16 citations

• CapsNets continuing the convolutional quest

  Sascha Diefenbacher, Hermann Frost, Gregor Kasieczka, Tilman Plehn, Jennifer M. Thompson

  SciPost Phys. 8, 023 (2020) · published 7 February 2020 | Toggle abstract · pdf

  Capsule networks are ideal tools to combine event-level and subjet information at the LHC. After benchmarking our capsule network against standard convolutional networks, we show how multi-class capsules extract a resonance decaying to top quarks from both, QCD di-jet and the top continuum backgrounds. We then show how its results can be easily interpreted. Finally, we use associated top-Higgs production to demonstrate that capsule networks can work on overlaying images to go beyond calorimeter information.

  16 citations

• Symmetries, safety, and self-supervision

  Barry M. Dillon, Gregor Kasieczka, Hans Olischlager, Tilman Plehn, Peter Sorrenson, Lorenz Vogel

  SciPost Phys. 12, 188 (2022) · published 9 June 2022 | Toggle abstract · pdf

  Collider searches face the challenge of defining a representation of high-dimensional data such that physical symmetries are manifest, the discriminating features are retained, and the choice of representation is new-physics agnostic. We introduce JetCLR to solve the mapping from low-level data to optimized observables though self-supervised contrastive learning. As an example, we construct a data representation for top and QCD jets using a permutation-invariant transformer-encoder network and visualize its symmetry properties. We compare the JetCLR representation with alternative representations using linear classifier tests and find it to work quite well.

  16 citations