{"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/lhc-analysis-specific-datasets-with","title":"LHC analysis-specific datasets with Generative Adversarial Networks","arxiv_id":"1901.05282","date":"2019-01-16","proceeding":null,"authors":["Bobak Hashemi","Nick Amin","Kaustuv Datta","Dominick Olivito","Maurizio Pierini"],"abstract":"Using generative adversarial networks (GANs), we investigate the possibility\nof creating large amounts of analysis-specific simulated LHC events at limited\ncomputing cost. This kind of generative model is analysis specific in the sense\nthat it directly generates the high-level features used in the last stage of a\ngiven physics analyses, learning the N-dimensional distribution of relevant\nfeatures in the context of a specific analysis selection. We apply this idea to\nthe generation of muon four-momenta in $Z \\to \\mu\\mu$ events at the LHC. We\nhighlight how use-case specific issues emerge when the distributions of the\nconsidered quantities exhibit particular features. We show how substantial\nperformance improvements and convergence speed-up can be obtained by including\nregression terms in the loss function of the generator. We develop an objective\ncriterion to assess the geenrator performance in a quantitative way. With\nfurther development, a generalization of this approach could substantially\nreduce the needed amount of centrally produced fully simulated events in large\nparticle physics experiments.","url_abs":"http://arxiv.org/abs/1901.05282v1","url_pdf":"http://arxiv.org/pdf/1901.05282v1.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":"lhc-analysis-specific-datasets-with","repo_url":"https://github.com/bth5032/DY-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1901.05282","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}