On Learnability, Complexity and Stability

TitleOn Learnability, Complexity and Stability
Publication TypeBook Chapter
Year of Publication2013
AuthorsVilla, S, Rosasco, L, Poggio, T, Schölkopf, B, Luo, Z, Vovk, V
Book TitleEmpirical Inference
Chapter7
Pagination59 - 69
PublisherSpringer Berlin Heidelberg
CityBerlin, Heidelberg
ISBN Number978-3-642-41135-9
Abstract

Empirical Inference, Chapter 7

Editors: Bernhard Schölkopf, Zhiyuan Luo and Vladimir Vovk

Abstract:

We consider the fundamental question of learnability of a hypothesis class in the supervised learning setting and in the general learning setting introduced by Vladimir Vapnik. We survey classic results characterizing learnability in terms of suitable notions of complexity, as well as more recent results that establish the connection between learnability and stability of a learning algorithm.

URLhttp://link.springer.com/10.1007/978-3-642-41136-6
DOI10.1007/978-3-642-41136-610.1007/978-3-642-41136-6_7

Download: 

Research Area: 

CBMM Relationship: 

  • CBMM Related