FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2743218360> ?p ?o ?g. }

• W2743218360 abstract "Modern machine learning techniques can be used to construct powerful models for difficult collider physics problems. In many applications, however, these models are trained on imperfect simulations due to a lack of truth-level information in the data, which risks the model learning artifacts of the simulation. In this paper, we introduce the paradigm of classification without labels (CWoLa) in which a classifier is trained to distinguish statistical mixtures of classes, which are common in collider physics. Crucially, neither individual labels nor class proportions are required, yet we prove that the optimal classifier in the CWoLa paradigm is also the optimal classifier in the traditional fully-supervised case where all label information is available. After demonstrating the power of this method in an analytical toy example, we consider a realistic benchmark for collider physics: distinguishing quark- versus gluon-initiated jets using mixed quark/gluon training samples. More generally, CWoLa can be applied to any classification problem where labels or class proportions are unknown or simulations are unreliable, but statistical mixtures of the classes are available." @default.
• W2743218360 created "2017-08-17" @default.
• W2743218360 creator A5020586743 @default.
• W2743218360 creator A5051781797 @default.
• W2743218360 creator A5054491740 @default.
• W2743218360 date "2017-10-01" @default.
• W2743218360 modified "2023-10-18" @default.
• W2743218360 title "Classification without labels: learning from mixed samples in high energy physics" @default.
• W2743218360 cites W1690836630 @default.
• W2743218360 cites W1907343197 @default.
• W2743218360 cites W2025343454 @default.
• W2743218360 cites W2066524694 @default.
• W2743218360 cites W2068177074 @default.
• W2743218360 cites W2099899058 @default.
• W2743218360 cites W2131899460 @default.
• W2743218360 cites W2136749405 @default.
• W2743218360 cites W2163097950 @default.
• W2743218360 cites W2231834475 @default.
• W2743218360 cites W2268579919 @default.
• W2743218360 cites W2269829830 @default.
• W2743218360 cites W2296754115 @default.
• W2743218360 cites W2357329924 @default.
• W2743218360 cites W2606891456 @default.
• W2743218360 cites W2963314381 @default.
• W2743218360 cites W3020995000 @default.
• W2743218360 cites W3037884215 @default.
• W2743218360 cites W3037961236 @default.
• W2743218360 cites W3098163999 @default.
• W2743218360 cites W3100634322 @default.
• W2743218360 cites W3100723510 @default.
• W2743218360 cites W3101170768 @default.
• W2743218360 cites W3101593275 @default.
• W2743218360 cites W3102141384 @default.
• W2743218360 cites W3103114583 @default.
• W2743218360 cites W3104023534 @default.
• W2743218360 cites W3104135668 @default.
• W2743218360 cites W3104561293 @default.
• W2743218360 cites W3104674222 @default.
• W2743218360 cites W3105222401 @default.
• W2743218360 cites W3105797459 @default.
• W2743218360 cites W3121614399 @default.
• W2743218360 cites W3122543598 @default.
• W2743218360 cites W4251448448 @default.
• W2743218360 doi "https://doi.org/10.1007/jhep10(2017)174" @default.
• W2743218360 hasPublicationYear "2017" @default.
• W2743218360 type Work @default.
• W2743218360 sameAs 2743218360 @default.
• W2743218360 citedByCount "142" @default.
• W2743218360 countsByYear W27432183602018 @default.
• W2743218360 countsByYear W27432183602019 @default.
• W2743218360 countsByYear W27432183602020 @default.
• W2743218360 countsByYear W27432183602021 @default.
• W2743218360 countsByYear W27432183602022 @default.
• W2743218360 countsByYear W27432183602023 @default.
• W2743218360 crossrefType "journal-article" @default.
• W2743218360 hasAuthorship W2743218360A5020586743 @default.
• W2743218360 hasAuthorship W2743218360A5051781797 @default.
• W2743218360 hasAuthorship W2743218360A5054491740 @default.
• W2743218360 hasBestOaLocation W27432183601 @default.
• W2743218360 hasConcept C109214941 @default.
• W2743218360 hasConcept C119857082 @default.
• W2743218360 hasConcept C121332964 @default.
• W2743218360 hasConcept C138885662 @default.
• W2743218360 hasConcept C152290109 @default.
• W2743218360 hasConcept C154945302 @default.
• W2743218360 hasConcept C184748400 @default.
• W2743218360 hasConcept C2780310539 @default.
• W2743218360 hasConcept C41008148 @default.
• W2743218360 hasConcept C41895202 @default.
• W2743218360 hasConcept C7602139 @default.
• W2743218360 hasConcept C95623464 @default.
• W2743218360 hasConceptScore W2743218360C109214941 @default.
• W2743218360 hasConceptScore W2743218360C119857082 @default.
• W2743218360 hasConceptScore W2743218360C121332964 @default.
• W2743218360 hasConceptScore W2743218360C138885662 @default.
• W2743218360 hasConceptScore W2743218360C152290109 @default.
• W2743218360 hasConceptScore W2743218360C154945302 @default.
• W2743218360 hasConceptScore W2743218360C184748400 @default.
• W2743218360 hasConceptScore W2743218360C2780310539 @default.
• W2743218360 hasConceptScore W2743218360C41008148 @default.
• W2743218360 hasConceptScore W2743218360C41895202 @default.
• W2743218360 hasConceptScore W2743218360C7602139 @default.
• W2743218360 hasConceptScore W2743218360C95623464 @default.
• W2743218360 hasIssue "10" @default.
• W2743218360 hasLocation W27432183601 @default.
• W2743218360 hasLocation W27432183602 @default.
• W2743218360 hasLocation W27432183603 @default.
• W2743218360 hasLocation W27432183604 @default.
• W2743218360 hasLocation W27432183605 @default.
• W2743218360 hasLocation W27432183606 @default.
• W2743218360 hasLocation W27432183607 @default.
• W2743218360 hasOpenAccess W2743218360 @default.
• W2743218360 hasPrimaryLocation W27432183601 @default.
• W2743218360 hasRelatedWork W1987690761 @default.
• W2743218360 hasRelatedWork W2027170592 @default.
• W2743218360 hasRelatedWork W2073464267 @default.
• W2743218360 hasRelatedWork W2075465983 @default.
• W2743218360 hasRelatedWork W2086948415 @default.
• W2743218360 hasRelatedWork W2271729901 @default.
• W2743218360 hasRelatedWork W3101195305 @default.

• next