Multivariate Analysis Methods in Particle Physics

Bhat, P. C.

doi:10.1146/annurev.nucl.012809.104427

Cited by 61 publications

(53 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…See ref. [45] for a brief review on various multivariate methods and their use in collider searches. In this paper, we only use multivariate techniques and do not compare our achieved sensitivity with the cut-based techniques.…”

Section: Multivariate Analysismentioning

confidence: 99%

Heavy charged scalars from $$ c\overline{s} $$ fusion: a generic search strategy applied to a 3HDM with U(1) × U(1) family symmetry

Camargo-Molina

Mandal

Pasechnik

et al. 2018

J. High Energ. Phys.

View full text Add to dashboard Cite

We describe a class of three Higgs doublet models (3HDMs) with a softly broken U(1) × U(1) family symmetry that enforces a Cabibbo-like quark mixing while forbidding tree-level flavour changing neutral currents. The hierarchy in the observed quark masses is partly explained by a softer hierarchy in the vacuum expectation values of the three Higgs doublets. As a consequence, the physical scalar spectrum contains a Standard Model (SM) like Higgs boson h 125 while exotic scalars couple the strongest to the second quark family, leading to rather unconventional discovery channels that could be probed at the Large Hadron Collider. In particular, we describe a search strategy for the lightest charged Higgs boson H ± , through the process cs → H + → W + h 125 , using a multivariate analysis that leads to an excellent discriminatory power against the SM background. Although the analysis is applied to the proposed class of 3HDMs, we employ a model-independent formulation such that it can be applied to any other model with the same discovery channel.

show abstract

Section: Multivariate Analysismentioning

confidence: 99%

Heavy charged scalars from $$ c\overline{s} $$ fusion: a generic search strategy applied to a 3HDM with U(1) × U(1) family symmetry

Camargo-Molina

Mandal

Pasechnik

et al. 2018

J. High Energ. Phys.

View full text Add to dashboard Cite

show abstract

“…Multivariate analysis (MVA) methods [20] have been extensively used in many aspects of the analyses, in all channels, to extract maximal information from data and obtain the best possible physics results. MVA methods are used in electron and photon identification, object energy corrections, vertex association, and signal/background discrimination.…”

Section: Searches For the Standard Model Higgs Bosonmentioning

confidence: 99%

Observation of a Higgs-like Boson in CMS at the LHC

Bhat

2013

Nuclear Physics B - Proceedings Supplements

Self Cite

View full text Add to dashboard Cite

After decades of pursuit at lepton and hadron colliders around the world, a Higgs-like boson has been observed at the Large Hadron Collider (LHC). We present results of searches by the CMS collaboration for the production of the standard model Higgs boson in proton-proton collisions, using data samples corresponding to integrated luminosities of 5.1 fb 1 at p s = 7 TeV and 5.3 fb 1 at p s = 8 TeV. The searches have been performed in five Higgs decay modes, , ZZ, WW, ⌧ + ⌧ , and bb, in the mass range from 110 up to 160 GeV. Multivariate methods have been used in many aspects of the analyses to extract optimal results. An excess of events has been observed above the expected background, with a significance of 5.0 standard deviations. Most of the excess is in the high resolution and ZZ decay modes. A fit to the signal in these modes yields a mass for the boson of 125.3±0.4(stat.)±0.5(syst.) GeV. Since the new boson decays into two photons, its spin can be inferred to be di↵erent from one.

show abstract

“…Such signals usually manifest themselves as tiny excesses of certain types of collision events in particle detectors and the data analysis challenge is to detect and extract these minute signals among a vast background of known physics. The problem can be tackled with the help of machine learning techniques which are an essential tool in improving the signal-to-background ratio in many modern physics analysis scenarios [8].…”

Section: Demonstration: Search For the Higgs Bosonmentioning

confidence: 99%

“…Traditionally, such analyses are conducted in a model-dependent mode [8], where one trains a supervised classifier to search for phenomena expected to be seen under some hypothetical model of new physics, such as supersymmetry, extra dimensions, etc.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised detection of collective anomalies with an application in high energy particle physics

Vatanen

Kuusela

Malmi

et al. 2012

The 2012 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-We study a novel type of a semi-supervised anomaly detection problem where the anomalies occur collectively among a background of normal data. Such problem arises in experimental high energy physics when one is trying to discover deviations from known Standard Model physics. We solve the problem by first fitting a mixture of Gaussians to a labeled background sample. We then fit a mixture of this background model and a number of additional Gaussians to an unlabeled sample containing both background and anomalies. This way we not only detect but also perform pattern recognition of anomalies. Such mixture model allows us to perform classification of anomalies vs. background, estimate the proportion of anomalies in the sample and study the statistical significance of the anomalous contribution. We first verify the performance of the method using artificial data and then demonstrate its real-life applicability using a data set related to the search of the Higgs boson at the Tevatron collider.

show abstract

Multivariate Analysis Methods in Particle Physics

Cited by 61 publications

References 64 publications

Heavy charged scalars from $$ c\overline{s} $$ fusion: a generic search strategy applied to a 3HDM with U(1) × U(1) family symmetry

Heavy charged scalars from $$ c\overline{s} $$ fusion: a generic search strategy applied to a 3HDM with U(1) × U(1) family symmetry

Observation of a Higgs-like Boson in CMS at the LHC

Semi-supervised detection of collective anomalies with an application in high energy particle physics

Contact Info

Product

Resources

About