Learning the latent structure of collider events
Abstract We describe a technique to learn the underlying structure of collider events directly from the data, without having a particular theoretical model in mind. It allows to infer aspects of the theoretical model that may have given rise to this structure, and can be used to cluster or classify...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-10-01
|
| Series: | Journal of High Energy Physics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/JHEP10(2020)206 |
| _version_ | 1818971847913373696 |
|---|---|
| author | B. M. Dillon D. A. Faroughy J. F. Kamenik M. Szewc |
| author_facet | B. M. Dillon D. A. Faroughy J. F. Kamenik M. Szewc |
| author_sort | B. M. Dillon |
| collection | DOAJ |
| description | Abstract We describe a technique to learn the underlying structure of collider events directly from the data, without having a particular theoretical model in mind. It allows to infer aspects of the theoretical model that may have given rise to this structure, and can be used to cluster or classify the events for analysis purposes. The unsupervised machine-learning technique is based on the probabilistic (Bayesian) generative model of Latent Dirichlet Allocation. We pair the model with an approximate inference algorithm called Variational Inference, which we then use to extract the latent probability distributions describing the learned underlying structure of collider events. We provide a detailed systematic study of the technique using two example scenarios to learn the latent structure of di-jet event samples made up of QCD background events and either t t ¯ $$ t\overline{t} $$ or hypothetical W′ → (ϕ → WW)W signal events. |
| first_indexed | 2024-12-20T14:58:53Z |
| format | Article |
| id | doaj.art-4c52965b60724362bcd20362e9605d9c |
| institution | Directory Open Access Journal |
| issn | 1029-8479 |
| language | English |
| last_indexed | 2024-12-20T14:58:53Z |
| publishDate | 2020-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of High Energy Physics |
| spelling | doaj.art-4c52965b60724362bcd20362e9605d9c2022-12-21T19:36:43ZengSpringerOpenJournal of High Energy Physics1029-84792020-10-0120201014810.1007/JHEP10(2020)206Learning the latent structure of collider eventsB. M. Dillon0D. A. Faroughy1J. F. Kamenik2M. Szewc3Jožef Stefan InstitutePhysik-Institut, Universität ZürichJožef Stefan InstituteInternational Center for Advanced Studies (ICAS) and CONICET, UNSAMAbstract We describe a technique to learn the underlying structure of collider events directly from the data, without having a particular theoretical model in mind. It allows to infer aspects of the theoretical model that may have given rise to this structure, and can be used to cluster or classify the events for analysis purposes. The unsupervised machine-learning technique is based on the probabilistic (Bayesian) generative model of Latent Dirichlet Allocation. We pair the model with an approximate inference algorithm called Variational Inference, which we then use to extract the latent probability distributions describing the learned underlying structure of collider events. We provide a detailed systematic study of the technique using two example scenarios to learn the latent structure of di-jet event samples made up of QCD background events and either t t ¯ $$ t\overline{t} $$ or hypothetical W′ → (ϕ → WW)W signal events.http://link.springer.com/article/10.1007/JHEP10(2020)206Jet substructureBeyond Standard ModelHadron-Hadron scattering (experiments)JetsParticle and resonance production |
| spellingShingle | B. M. Dillon D. A. Faroughy J. F. Kamenik M. Szewc Learning the latent structure of collider events Journal of High Energy Physics Jet substructure Beyond Standard Model Hadron-Hadron scattering (experiments) Jets Particle and resonance production |
| title | Learning the latent structure of collider events |
| title_full | Learning the latent structure of collider events |
| title_fullStr | Learning the latent structure of collider events |
| title_full_unstemmed | Learning the latent structure of collider events |
| title_short | Learning the latent structure of collider events |
| title_sort | learning the latent structure of collider events |
| topic | Jet substructure Beyond Standard Model Hadron-Hadron scattering (experiments) Jets Particle and resonance production |
| url | http://link.springer.com/article/10.1007/JHEP10(2020)206 |
| work_keys_str_mv | AT bmdillon learningthelatentstructureofcolliderevents AT dafaroughy learningthelatentstructureofcolliderevents AT jfkamenik learningthelatentstructureofcolliderevents AT mszewc learningthelatentstructureofcolliderevents |