Show simple item record

dc.contributor.authorBevan, Aen_US
dc.contributor.authorGoñi, RGen_US
dc.contributor.authorHays, Jen_US
dc.contributor.authorStevenson, Ten_US
dc.contributor.author22nd International Conference on Computing in High Energy and Nuclear Physics (CHEP 2016)en_US
dc.date.accessioned2018-01-11T16:01:32Z
dc.date.available2017-07-18en_US
dc.date.issued2017-11-23en_US
dc.date.submitted2018-01-04T03:45:21.758Z
dc.identifier.issn1742-6588en_US
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/31266
dc.description.abstract© Published under licence by IOP Publishing Ltd. We review the concept of Support Vector Machines (SVMs) and discuss examples of their use in a number of scenarios. Several SVM implementations have been used in HEP and we exemplify this algorithm using the Toolkit for Multivariate Analysis (TMVA) implementation. We discuss examples relevant to HEP including background suppression for H → τ + τ - at the LHC with several different kernel functions. Performance benchmarking leads to the issue of generalisation of hyper-parameter selection. The avoidance of fine tuning (over training or over fitting) in MVA hyper-parameter optimisation, i.e. the ability to ensure generalised performance of an MVA that is independent of the training, validation and test samples, is of utmost importance. We discuss this issue and compare and contrast performance of hold-out and k-fold cross-validation. We have extended the SVM functionality and introduced tools to facilitate cross validation in TMVA and present results based on these improvements.en_US
dc.rightsContent from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
dc.titleSupport vector machines and generalisation in HEPen_US
dc.typeConference Proceeding
dc.rights.holder© The Author(s) 2017
dc.identifier.doi10.1088/1742-6596/898/7/072021en_US
pubs.issue7en_US
pubs.notesNot knownen_US
pubs.publication-statusPublisheden_US
pubs.volume898en_US
dcterms.dateAccepted2017-07-18en_US
qmul.funderParticle Physics Consolodated Grant 2012-2016::Science and Technology Facilities Council [2006-2012]en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record