{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-guide-to-constraining-effective-field","title":"A Guide to Constraining Effective Field Theories with Machine Learning","arxiv_id":"1805.00020","date":"2018-04-30","proceeding":null,"authors":["Johann Brehmer","Kyle Cranmer","Gilles Louppe","Juan Pavez"],"abstract":"We develop, discuss, and compare several inference techniques to constrain\ntheory parameters in collider experiments. By harnessing the latent-space\nstructure of particle physics processes, we extract extra information from the\nsimulator. This augmented data can be used to train neural networks that\nprecisely estimate the likelihood ratio. The new methods scale well to many\nobservables and high-dimensional parameter spaces, do not require any\napproximations of the parton shower and detector response, and can be evaluated\nin microseconds. Using weak-boson-fusion Higgs production as an example\nprocess, we compare the performance of several techniques. The best results are\nfound for likelihood ratio estimators trained with extra information about the\nscore, the gradient of the log likelihood function with respect to the theory\nparameters. The score also provides sufficient statistics that contain all the\ninformation needed for inference in the neighborhood of the Standard Model.\nThese methods enable us to put significantly stronger bounds on effective\ndimension-six operators than the traditional approach based on histograms. They\nalso outperform generic machine learning methods that do not make use of the\nparticle physics structure, demonstrating their potential to substantially\nimprove the new physics reach of the LHC legacy results.","url_abs":"http://arxiv.org/abs/1805.00020v4","url_pdf":"http://arxiv.org/pdf/1805.00020v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-guide-to-constraining-effective-field","repo_url":"https://github.com/johannbrehmer/higgs_inference","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-guide-to-constraining-effective-field","repo_url":"https://github.com/johannbrehmer/simulator-mining-example","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.00020","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}