| Article | |
| Report number | arXiv:2107.02779 |
| Title | Pile-Up Mitigation using Attention |
| Author(s) | Maier, Benedikt (CERN) ; Narayanan, Siddharth M. (CERN) ; de Castro, Gianfranco (Caltech, Pasadena (main)) ; Goncharov, Maxim (MIT) ; Paus, Christoph (MIT) ; Schott, Matthias (Mainz U.) |
| Publication | 2022-06-06 |
| Imprint | 2021-07-06 |
| Number of pages | 17 |
| Note | 17 pages, 6 figures, final published version |
| In: | Mach. Learn. Sci. Tech. 3 (2022) 025012 |
| DOI | 10.1088/2632-2153/ac7198 |
| Subject category | hep-ex ; Particle Physics - Experiment ; physics.ins-det ; Detectors and Experimental Techniques |
| Abstract | Particle production from secondary proton-proton collisions, commonly referred to as pile-up, impair the sensitivity of both new physics searches and precision measurements at LHC experiments. We propose a novel algorithm, PUMA, for identifying pile-up objects with the help of deep neural networks based on sparse transformers. These attention mechanisms were developed for natural language processing but have become popular in other applications. In a realistic detector simulation, our method outperforms classical benchmark algorithms for pile-up mitigation in key observables. It provides a perspective for mitigating the effects of pile-up in the high luminosity era of the LHC, where up to 200 proton-proton collisions are expected to occur simultaneously. |
| Copyright/License | preprint: (License: arXiv nonexclusive-distrib 1.0) publication: © 2022 The Author(s) (License: CC-BY-4.0) |
Corresponding record in: Inspire
ჩანაწერი შექმნილია 2021-08-05, ბოლოს შესწორებულია 2023-03-30
PDF