Machine learning uncertainties with adversarial neural networks
Machine Learning is a powerful tool to reveal and exploit correlations in a multi-dimensional parameter space. Making predictions from such correlations is a highly non-trivial task, in particular when the details of the underlying dynamics of a theoretical model are not fully understood. Using adve...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Berlin Heidelberg
2019
|
| Online Access: | http://hdl.handle.net/1721.1/120361 https://orcid.org/0000-0001-8189-3741 |
| _version_ | 1826209019742650368 |
|---|---|
| author | Englert, Christoph Galler, Peter Spannowsky, Michael Harris, Philip Coleman |
| author2 | Massachusetts Institute of Technology. Department of Physics |
| author_facet | Massachusetts Institute of Technology. Department of Physics Englert, Christoph Galler, Peter Spannowsky, Michael Harris, Philip Coleman |
| author_sort | Englert, Christoph |
| collection | MIT |
| description | Machine Learning is a powerful tool to reveal and exploit correlations in a multi-dimensional parameter space. Making predictions from such correlations is a highly non-trivial task, in particular when the details of the underlying dynamics of a theoretical model are not fully understood. Using adversarial networks, we include a priori known sources of systematic and theoretical uncertainties during the training. This paves the way to a more reliable event classification on an event-by-event basis, as well as novel approaches to perform parameter fits of particle physics data. We demonstrate the benefits of the method explicitly in an example considering effective field theory extensions of Higgs boson production in association with jets. |
| first_indexed | 2024-09-23T14:16:04Z |
| format | Article |
| id | mit-1721.1/120361 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T14:16:04Z |
| publishDate | 2019 |
| publisher | Springer Berlin Heidelberg |
| record_format | dspace |
| spelling | mit-1721.1/1203612022-10-01T20:15:34Z Machine learning uncertainties with adversarial neural networks Englert, Christoph Galler, Peter Spannowsky, Michael Harris, Philip Coleman Massachusetts Institute of Technology. Department of Physics Harris, Philip Coleman Machine Learning is a powerful tool to reveal and exploit correlations in a multi-dimensional parameter space. Making predictions from such correlations is a highly non-trivial task, in particular when the details of the underlying dynamics of a theoretical model are not fully understood. Using adversarial networks, we include a priori known sources of systematic and theoretical uncertainties during the training. This paves the way to a more reliable event classification on an event-by-event basis, as well as novel approaches to perform parameter fits of particle physics data. We demonstrate the benefits of the method explicitly in an example considering effective field theory extensions of Higgs boson production in association with jets. Massachusetts Institute of Technology. Department of Physics 2019-02-13T20:39:01Z 2019-02-13T20:39:01Z 2019-01 2018-08 2019-01-04T05:06:45Z Article http://purl.org/eprint/type/JournalArticle 1434-6044 1434-6052 http://hdl.handle.net/1721.1/120361 Englert, Christoph, et al. “Machine Learning Uncertainties with Adversarial Neural Networks.” The European Physical Journal C, vol. 79, no. 1, Jan. 2019. © 2018 The Authors https://orcid.org/0000-0001-8189-3741 en https://doi.org/10.1140/epjc/s10052-018-6511-8 The European Physical Journal C Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer Berlin Heidelberg Springer Berlin Heidelberg |
| spellingShingle | Englert, Christoph Galler, Peter Spannowsky, Michael Harris, Philip Coleman Machine learning uncertainties with adversarial neural networks |
| title | Machine learning uncertainties with adversarial neural networks |
| title_full | Machine learning uncertainties with adversarial neural networks |
| title_fullStr | Machine learning uncertainties with adversarial neural networks |
| title_full_unstemmed | Machine learning uncertainties with adversarial neural networks |
| title_short | Machine learning uncertainties with adversarial neural networks |
| title_sort | machine learning uncertainties with adversarial neural networks |
| url | http://hdl.handle.net/1721.1/120361 https://orcid.org/0000-0001-8189-3741 |
| work_keys_str_mv | AT englertchristoph machinelearninguncertaintieswithadversarialneuralnetworks AT gallerpeter machinelearninguncertaintieswithadversarialneuralnetworks AT spannowskymichael machinelearninguncertaintieswithadversarialneuralnetworks AT harrisphilipcoleman machinelearninguncertaintieswithadversarialneuralnetworks |