Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/71063
Type: Conference paper
Title: Is margin preserved after random projection?
Author: Shi, Q.
Shen, C.
Hill, R.
Van Den Hengel, A.
Citation: Proceedings of the 29th International Conference on Machine Learning, held in Edinburgh, Scotland, UK, 27 June-3 July 2012 / J. Langford and J. Pineau (eds.): pp. 591-598
Publisher: Omnipress
Publisher Place: USA
Issue Date: 2012
ISBN: 9781450312851
Conference Name: International Conference on Machine Learning (29th : 2012 : Edinburgh, Scotland)
Statement of
Responsibility: 
Qinfeng Shi, Chunhua Shen, Rhys Hill, Anton van den Hengel
Abstract: Random projections have been applied in many machine learning algorithms. However, whether margin is preserved after random projection is non-trivial and not well studied. In this paper we analyse margin distortion after random projection, and give the conditions of margin preservation for binary classification problems. We also extend our analysis to margin for multiclass problems, and provide theoretical bounds on multiclass margin on the projected data.
Rights: Copyright 2012 by the author(s)/owner(s).
RMID: 0020125270
Description (link): http://arxiv.org/html/1207.4676v1
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_71063.pdfAccepted version557.47 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.