Pileup Mitigation with Machine Learning (PUMML)
Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network ta...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Berlin Heidelberg
2018
|
| Online Access: | http://hdl.handle.net/1721.1/113351 |
| _version_ | 1826214805416968192 |
|---|---|
| author | Nachman, Benjamin Schwartz, Matthew D. Komiske, Patrick T. Metodiev, Eric Mario |
| author2 | Massachusetts Institute of Technology. Department of Physics |
| author_facet | Massachusetts Institute of Technology. Department of Physics Nachman, Benjamin Schwartz, Matthew D. Komiske, Patrick T. Metodiev, Eric Mario |
| author_sort | Nachman, Benjamin |
| collection | MIT |
| description | Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data. Keywords: Jets. |
| first_indexed | 2024-09-23T16:11:26Z |
| format | Article |
| id | mit-1721.1/113351 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:11:26Z |
| publishDate | 2018 |
| publisher | Springer Berlin Heidelberg |
| record_format | dspace |
| spelling | mit-1721.1/1133512022-10-02T06:57:47Z Pileup Mitigation with Machine Learning (PUMML) Nachman, Benjamin Schwartz, Matthew D. Komiske, Patrick T. Metodiev, Eric Mario Massachusetts Institute of Technology. Department of Physics Komiske, Patrick T. Metodiev, Eric Mario Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data. Keywords: Jets. United States. Department of Energy. Office of Science (Contract DE-AC02-05CH11231) United States. Department of Energy. Office of Science (Contract DE-SC0013607) United States. Department of Energy. Office of Nuclear Physics (Contract DE-SC0011090) United States. Department of Energy. Office of High Energy and Nuclear Physics (Contract DE-SC0012567) 2018-01-30T19:05:20Z 2018-01-30T19:05:20Z 2017-12 2017-12-14T06:33:17Z Article http://purl.org/eprint/type/JournalArticle 1029-8479 1126-6708 http://hdl.handle.net/1721.1/113351 Komiske, Patrick T., et al. “Pileup Mitigation with Machine Learning (PUMML).” Journal of High Energy Physics, vol. 2017, no. 12, Dec. 2017. en http://dx.doi.org/10.1007/JHEP12(2017)051 Journal of High Energy Physics Creative Commons Attribution http://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer Berlin Heidelberg Springer Berlin Heidelberg |
| spellingShingle | Nachman, Benjamin Schwartz, Matthew D. Komiske, Patrick T. Metodiev, Eric Mario Pileup Mitigation with Machine Learning (PUMML) |
| title | Pileup Mitigation with Machine Learning (PUMML) |
| title_full | Pileup Mitigation with Machine Learning (PUMML) |
| title_fullStr | Pileup Mitigation with Machine Learning (PUMML) |
| title_full_unstemmed | Pileup Mitigation with Machine Learning (PUMML) |
| title_short | Pileup Mitigation with Machine Learning (PUMML) |
| title_sort | pileup mitigation with machine learning pumml |
| url | http://hdl.handle.net/1721.1/113351 |
| work_keys_str_mv | AT nachmanbenjamin pileupmitigationwithmachinelearningpumml AT schwartzmatthewd pileupmitigationwithmachinelearningpumml AT komiskepatrickt pileupmitigationwithmachinelearningpumml AT metodievericmario pileupmitigationwithmachinelearningpumml |