ScienceDirect® Home Skip Main Navigation Links
You have guest access to ScienceDirect. Find out more.
 
Home
Browse
My Settings
Alerts
Help
 Quick Search
 Search tips (Opens new window)
    Clear all fields    
 
Font Size: Decrease Font Size  Increase Font Size
 Abstract - selected
Purchase PDF (111 K)

Article Toolbox
 
 
 
Related Articles in ScienceDirect
View More Related Articles
 
View Record in Scopus
 
doi:10.1016/S0304-3975(00)00134-1    
How to Cite or Link Using DOI (Opens New Window)

Copyright © 2001 Elsevier Science B.V. All rights reserved.

A note on a scale-sensitive dimension of linear bounded functionals in Banach spaces

Purchase the full-text article



References and further reading may be available for this article. To view references and further reading you must purchase this article.

Leonid Gurvits1, Corresponding Author Contact Information, E-mail The Corresponding Author, , a, , b

a NEC Research Institute, 4 Independence Way, Princeton, NJ 08540, USA

b DIMACS, Rutgers University, New Brunswick, NJ 08903, USA


Available online 4 June 2001.

Abstract

We show that “B is of type p>1” is a necessary and sufficient condition for a learnability of a class of linear bounded functionals with norm less-than-or-equals, slant1 restricted to the unit ball in Banach space B. On the way, we give very short probabilistic proof for Vapnik's result (Hilbert space and improved) and improve our result with Pascal Koiran for convex halls of indicator functions. The approach we use in this paper allows to connect various results about learnability and approximation.

Author Keywords: VC-dimension; Scale-sensitive dimension; Banach spaces

1 Research at Rutgers partially supported by the US Air Force Grant AFOSR-94-0293.

Corresponding Author Contact Information Correspondence address. NEC Research Institute, 4 Independence Way, Princeton, N5 08540, USA; email: gurvits@research.nj.nec.com


 
Home
Browse
My Settings
Alerts
Help
Elsevier.com (Opens new window)
About ScienceDirect  |  Contact Us  |  Information for Advertisers  |  Terms & Conditions  |  Privacy Policy
Copyright © 2009 Elsevier B.V. All rights reserved. ScienceDirect® is a registered trademark of Elsevier B.V.