A Caltech Library Service

Pile-up mitigation using attention

Maier, B. and Narayanan, S. M. and de Castro, G. and Goncharov, M. and Paus, Ch. and Schott, M. (2022) Pile-up mitigation using attention. Machine Learning: Science and Technology, 3 (2). Art. No. 025012. ISSN 2632-2153. doi:10.1088/2632-2153/ac7198.

[img] PDF - Published Version
Creative Commons Attribution.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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 large hadron collider (LHC) experiments. We propose a novel algorithm, Puma, for modeling pile-up 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.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Maier, B.0000-0001-5270-7540
Schott, M.0000-0002-4235-7265
Additional Information:© 2022 The Author(s). Published by IOP Publishing Ltd. Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. Received 1 November 2021. Accepted 19 May 2022. Published 6 June 2022. The authors would like to thank Philip Harris and Lindsey Gray for productive conversations and feedback. The networks presented in this paper have been trained on the MIT-IBM Satori GPU cluster and on the Tier-2 MIT computing cluster. This material is based upon work supported by the U.S. National Science Foundation under Award Number PHY-1624356 and the U.S. Department of Energy Office of Science Office of Nuclear Physics under Award Number DE-SC0011939. Data availability statement. The data that support the findings of this study are available upon reasonable request from the authors. Disclaimer: 'This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.'
Funding AgencyGrant Number
Department of Energy (DOE)DE-SC0011939
Subject Keywords:LHC, HL-LHC, pile-up, transformers, machine learning
Issue or Number:2
Record Number:CaltechAUTHORS:20220722-768890000
Persistent URL:
Official Citation:B Maier et al 2022 Mach. Learn.: Sci. Technol. 3 025012
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:115774
Deposited By: George Porter
Deposited On:26 Jul 2022 20:13
Last Modified:26 Jul 2022 20:13

Repository Staff Only: item control page