A Bound on the Performance of LDA in Randomly Projected Data Spaces

Robert Durrant, Ata Kaban

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We consider the problem of classification in nonadaptive dimensionality reduction. Specifically, we bound the increase in classification error of Fisher's Linear Discriminant classifier resulting from randomly projecting the high dimensional data into a lower dimensional space and both learning the classifier and performing the classification in the projected space. Our bound is reasonably tight, and unlike existing bounds on learning from randomly projected data, it becomes tighter as the quantity of training data increases without requiring any sparsity structure from the data.
Original languageEnglish
Title of host publication2010 20th International Conference on Pattern Recognition (ICPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages4044-4047
Number of pages4
ISBN (Print)978-1-4244-7542-1
DOIs
Publication statusPublished - 26 Aug 2010
EventInternational Conference on Pattern Recognition (ICPR 2010), 20th - Istanbul, Turkey
Duration: 23 Aug 201026 Aug 2010

Conference

ConferenceInternational Conference on Pattern Recognition (ICPR 2010), 20th
Country/TerritoryTurkey
CityIstanbul
Period23/08/1026/08/10

Fingerprint

Dive into the research topics of 'A Bound on the Performance of LDA in Randomly Projected Data Spaces'. Together they form a unique fingerprint.

Cite this