Buchumschlag

Understanding event-generation networks via uncertainties

Weitere Versionen anzeigen (1)

Following the growing success of generative neural networks in LHC simulations, the crucial question is how to control the networks and assign uncertainties to their event output. We show how Bayesian normalizing flow or invertible networks capture uncertainties from the training and turn them into...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bellagente, Marco (VerfasserIn) , Haußmann, Manuel (VerfasserIn) , Luchmann, Michel (VerfasserIn) , Plehn, Tilman (VerfasserIn)
Dokumenttyp: Article (Journal) Kapitel/Artikel
Sprache:Englisch
Veröffentlicht: October 4, 2021
In: Arxiv
Year: 2021, Pages: 1-26
DOI:10.48550/arXiv.2104.04543
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.2104.04543
Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2104.04543
Volltext
Verfasserangaben:Marco Bellagente, Manuel Haußmann, Michel Luchmann, and Tilman Plehn

MARC

LEADER 00000caa a2200000 c 4500
001 1810080991
003 DE-627
005 20220820222443.0
007 cr uuu---uuuuu
008 220713s2021 xx |||||o 00| ||eng c
024 7 |a 10.48550/arXiv.2104.04543  |2 doi 
035 |a (DE-627)1810080991 
035 |a (DE-599)KXP1810080991 
035 |a (OCoLC)1341463802 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 29  |2 sdnb 
100 1 |a Bellagente, Marco  |d 1993-  |e VerfasserIn  |0 (DE-588)1211496058  |0 (DE-627)1699769591  |4 aut 
245 1 0 |a Understanding event-generation networks via uncertainties  |c Marco Bellagente, Manuel Haußmann, Michel Luchmann, and Tilman Plehn 
264 1 |c October 4, 2021 
300 |a 26 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 13.07.2022 
520 |a Following the growing success of generative neural networks in LHC simulations, the crucial question is how to control the networks and assign uncertainties to their event output. We show how Bayesian normalizing flow or invertible networks capture uncertainties from the training and turn them into an uncertainty on the event weight. Fundamentally, the interplay between density and uncertainty estimates indicates that these networks learn functions in analogy to parameter fits rather than binned event counts. 
650 4 |a High Energy Physics - Phenomenology 
700 1 |a Haußmann, Manuel  |d 1990-  |e VerfasserIn  |0 (DE-588)1205492046  |0 (DE-627)1691155802  |4 aut 
700 1 |a Luchmann, Michel  |d 1994-  |e VerfasserIn  |0 (DE-588)1205492771  |0 (DE-627)1691156868  |4 aut 
700 1 |a Plehn, Tilman  |d 1969-  |e VerfasserIn  |0 (DE-588)1021935573  |0 (DE-627)715839535  |0 (DE-576)363449809  |4 aut 
773 0 8 |i Enthalten in  |t Arxiv  |d Ithaca, NY : Cornell University, 1991  |g (2021), Artikel-ID 2104.04543, Seite 1-26  |h Online-Ressource  |w (DE-627)509006531  |w (DE-600)2225896-6  |w (DE-576)28130436X  |7 nnas  |a Understanding event-generation networks via uncertainties 
773 1 8 |g year:2021  |g elocationid:2104.04543  |g pages:1-26  |g extent:26  |a Understanding event-generation networks via uncertainties 
856 4 0 |u https://doi.org/10.48550/arXiv.2104.04543  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u http://arxiv.org/abs/2104.04543  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20220713 
993 |a Article 
998 |g 1021935573  |a Plehn, Tilman  |m 1021935573:Plehn, Tilman  |d 130000  |d 130300  |d 700000  |d 728500  |e 130000PP1021935573  |e 130300PP1021935573  |e 700000PP1021935573  |e 728500PP1021935573  |k 0/130000/  |k 1/130000/130300/  |k 0/700000/  |k 1/700000/728500/  |p 4  |y j 
998 |g 1205492771  |a Luchmann, Michel  |m 1205492771:Luchmann, Michel  |d 130000  |d 130300  |e 130000PL1205492771  |e 130300PL1205492771  |k 0/130000/  |k 1/130000/130300/  |p 3 
998 |g 1205492046  |a Haußmann, Manuel  |m 1205492046:Haußmann, Manuel  |d 110000  |e 110000PH1205492046  |k 0/110000/  |p 2 
998 |g 1211496058  |a Bellagente, Marco  |m 1211496058:Bellagente, Marco  |d 130000  |e 130000PB1211496058  |k 0/130000/  |p 1  |x j 
999 |a KXP-PPN1810080991  |e 4165061964 
BIB |a Y 
JSO |a {"person":[{"display":"Bellagente, Marco","roleDisplay":"VerfasserIn","role":"aut","family":"Bellagente","given":"Marco"},{"role":"aut","display":"Haußmann, Manuel","roleDisplay":"VerfasserIn","given":"Manuel","family":"Haußmann"},{"display":"Luchmann, Michel","roleDisplay":"VerfasserIn","role":"aut","family":"Luchmann","given":"Michel"},{"display":"Plehn, Tilman","roleDisplay":"VerfasserIn","role":"aut","family":"Plehn","given":"Tilman"}],"title":[{"title_sort":"Understanding event-generation networks via uncertainties","title":"Understanding event-generation networks via uncertainties"}],"type":{"bibl":"chapter","media":"Online-Ressource"},"note":["Gesehen am 13.07.2022"],"language":["eng"],"recId":"1810080991","name":{"displayForm":["Marco Bellagente, Manuel Haußmann, Michel Luchmann, and Tilman Plehn"]},"origin":[{"dateIssuedKey":"2021","dateIssuedDisp":"October 4, 2021"}],"id":{"doi":["10.48550/arXiv.2104.04543"],"eki":["1810080991"]},"physDesc":[{"extent":"26 S."}],"relHost":[{"pubHistory":["1991 -"],"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"part":{"year":"2021","pages":"1-26","text":"(2021), Artikel-ID 2104.04543, Seite 1-26","extent":"26"},"disp":"Understanding event-generation networks via uncertaintiesArxiv","note":["Gesehen am 28.05.2024"],"type":{"media":"Online-Ressource","bibl":"edited-book"},"recId":"509006531","language":["eng"],"title":[{"title_sort":"Arxiv","title":"Arxiv"}],"physDesc":[{"extent":"Online-Ressource"}],"origin":[{"dateIssuedDisp":"1991-","dateIssuedKey":"1991","publisher":"Cornell University ; Arxiv.org","publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]"}],"id":{"eki":["509006531"],"zdb":["2225896-6"]}}]} 
SRT |a BELLAGENTEUNDERSTAND4202 

Ähnliche Einträge