Probing stop pair production at the LHC with graph neural networks

Abdughani, Murat; Ren, Jie; Wu, Lei; Yang, Jin Min

doi:10.1007/jhep08(2019)055

Cited by 62 publications

(45 citation statements)

References 65 publications

(65 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another important ML method, that could be explored in the context of displaced objects, is Graph Neural Network (GNN), which directly operates on the graph structure. GNNs have found extensive use in many other high-energy physics applications [93][94][95].…”

Section: Discussionmentioning

confidence: 99%

Study of energy deposition patterns in hadron calorimeter for prompt and displaced jets using convolutional neural network

Bhattacherjee

Mukherjee

Sengupta

2019

J. High Energ. Phys.

View full text Add to dashboard Cite

Sophisticated machine learning techniques have promising potential in search for physics beyond Standard Model in Large Hadron Collider (LHC). Convolutional neural networks (CNN) can provide powerful tools for differentiating between patterns of calorimeter energy deposits by prompt particles of Standard Model and long-lived particles predicted in various models beyond the Standard Model. We demonstrate the usefulness of CNN by using a couple of physics examples from well motivated BSM scenarios predicting long-lived particles giving rise to displaced jets. Our work suggests that modern machinelearning techniques have potential to discriminate between energy deposition patterns of prompt and long-lived particles, and thus, they can be useful tools in such searches.

show abstract

Section: Discussionmentioning

confidence: 99%

Study of energy deposition patterns in hadron calorimeter for prompt and displaced jets using convolutional neural network

Bhattacherjee

Mukherjee

Sengupta

2019

J. High Energ. Phys.

View full text Add to dashboard Cite

show abstract

“…Motivated by the early results of Ref. [25], graph networks have been also applied to other high energy physics tasks, such as event topology classification [27,28], particle tracking in a collider detector [29], pileup subtraction at the LHC [30], and particle reconstruction in irregular calorimeters [31].…”

Section: Related Workmentioning

confidence: 99%

JEDI-net: a jet identification algorithm based on interaction networks

et al. 2020

View full text Add to dashboard Cite

We investigate the performance of a jet identification algorithm based on interaction networks (JEDInet) to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The jet dynamics are described as a set of one-to-one interactions between the jet constituents. Based on a representation learned from these interactions, the jet is associated to one of the considered categories. Unlike other architectures, the JEDI-net models achieve their performance without special handling of the sparse input jet representation, extensive pre-processing, particle ordering, or specific assumptions regarding the underlying detector geometry. The presented models give better results with less model parameters, offering interesting prospects for LHC applications.

show abstract

“…Graph networks [47,71,73,93] and the related particle flow networks [94] have recently been used for other kinds of jet tagging, matching or exceeding the performances of other DL approaches, for event classification [95,96], for charged particle tracking in a silicon detector [97,98], for mitigation of the effects pileup [99], and for particle reconstruction in irregular calorimeters [98,[100][101][102] and the IceCube experiment [96].…”

Section: Related Workmentioning

confidence: 99%

Interaction networks for the identification of boosted H→bb¯ decays

et al. 2020

View full text Add to dashboard Cite

We develop an algorithm based on an interaction network to identify high-transverse-momentum Higgs bosons decaying to bottom quark-antiquark pairs and distinguish them from ordinary jets that reflect the configurations of quarks and gluons at short distances. The algorithm's inputs are features of the reconstructed charged particles in a jet and the secondary vertices associated with them. Describing the jet shower as a combination of particle-to-particle and particle-to-vertex interactions, the model is trained to learn a jet representation on which the classification problem is optimized. The algorithm is trained on simulated samples of realistic LHC collisions, released by the CMS Collaboration on the CERN Open Data Portal. The interaction network achieves a drastic improvement in the identification performance with respect to state-of-the-art algorithms.

show abstract

Probing stop pair production at the LHC with graph neural networks

Cited by 62 publications

References 65 publications

Study of energy deposition patterns in hadron calorimeter for prompt and displaced jets using convolutional neural network

Study of energy deposition patterns in hadron calorimeter for prompt and displaced jets using convolutional neural network

JEDI-net: a jet identification algorithm based on interaction networks

Interaction networks for the identification of boosted H→bb¯ decays

Contact Info

Product

Resources

About