Please use this identifier to cite or link to this item: https://doi.org/10.1109/18.915700
Title: The one-inclusion graph algorithm is near-optimal for the prediction model of learning
Authors: Li, Y. 
Long, P.M. 
Srinivasan, A. 
Keywords: Computational learning
One-inclusion graph algorithm
Prediction model
Sample complexity
Vapnik-Chervonenkis (VC) dimension
Issue Date: 2001
Source: Li, Y., Long, P.M., Srinivasan, A. (2001). The one-inclusion graph algorithm is near-optimal for the prediction model of learning. IEEE Transactions on Information Theory 47 (3) : 1257-1261. ScholarBank@NUS Repository. https://doi.org/10.1109/18.915700
Abstract: Haussler, Littlestone, and Warmuth described a general-purpose algorithm for learning according to the prediction model, and proved an upper bound on the probability that their algorithm makes a mistake in terms of the number of examples seen and the Vapnik-Chervonenkis (VC) dimension of the concept class being learned. We show that their bound is within a factor of 1 + o(1) of the best possible such bound for any algorithm.
Source Title: IEEE Transactions on Information Theory
URI: http://scholarbank.nus.edu.sg/handle/10635/43369
ISSN: 00189448
DOI: 10.1109/18.915700
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

8
checked on Dec 6, 2017

WEB OF SCIENCETM
Citations

1
checked on Nov 18, 2017

Page view(s)

87
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


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