2021
DOI: 10.1103/physrevd.103.074022
|View full text |Cite
|
Sign up to set email alerts
|

Equivariant energy flow networks for jet tagging

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
19
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
5

Relationship

1
9

Authors

Journals

citations
Cited by 37 publications
(19 citation statements)
references
References 54 publications
0
19
0
Order By: Relevance
“…Given the success of zooming, an alternative approach would be to consider scale transformations as a symmetry of the data and embed this information into the network architecture itself. There already exists work on jet taggers that are equivariant to other symmetries of jets [65][66][67][68] as well as implementations of scaling-equivariant CNNs [69][70][71]. Of course, in applications where the relationship between domains is less easily understood, it may not be possible to identify the appropriate data augmentation procedure.…”
Section: Resultsmentioning
confidence: 99%
“…Given the success of zooming, an alternative approach would be to consider scale transformations as a symmetry of the data and embed this information into the network architecture itself. There already exists work on jet taggers that are equivariant to other symmetries of jets [65][66][67][68] as well as implementations of scaling-equivariant CNNs [69][70][71]. Of course, in applications where the relationship between domains is less easily understood, it may not be possible to identify the appropriate data augmentation procedure.…”
Section: Resultsmentioning
confidence: 99%
“…As shown in Refs. [35,[49][50][51][52][53][54][55][56][57][58], this provides a more natural jet representation compared to alternative approaches based on jet images [59][60][61][62][63][64][65][66][67][68] or ordered lists of jet constituents [69][70][71][72][73][74][75][76][77] and translates to an improved tagging performance. A hierarchical learning approach using convolution operations [78] is adopted.…”
Section: The Flavour Tagging Algorithmmentioning
confidence: 99%
“…Based on the theory and phenomenology of jet physics, many expert-designed high-level jet substructure observables are constructed for jet tagging [2][3][4][5][6][7]. Using different jet representations, various deep learning approaches have been investigated in recent years: Multilayer perceptrons (MLPs) can be trained on a collection of jet-level observables [8][9][10][11][12][13]; 2D convolutional neural networks (CNNs) are applied to jet images [14][15][16][17][18][19][20][21][22][23][24][25][26][27]; MLPs, 1D CNNs, and recurrent neural networks are used to process a jet as a sequence of its constituent particles [28][29][30][31][32][33][34][35][36]; Graph neural networks (GNNs) are developed for the "particle cloud", i.e., an unordered set of particles [37][38][39][40][41][42][43][44][45][46]…”
Section: Introductionmentioning
confidence: 99%