Is margin preserved after random projection?

Files

hdl_71063.pdf (557.47 KB)
  (Accepted version)

Date

2012

Authors

Shi, Q.
Shen, C.
Hill, R.
Van Den Hengel, A.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

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

Statement of Responsibility

Qinfeng Shi, Chunhua Shen, Rhys Hill, Anton van den Hengel

Conference Name

International Conference on Machine Learning (29th : 2012 : Edinburgh, Scotland)

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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright 2012 by the author(s)/owner(s).

License

Grant ID

Published Version

Call number

Persistent link to this record