When is small beautiful?
(2003) 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003 2777. p.729-730- Abstract
- The basic bound on the generalisation error of a PAC learner makes the assumption that a consistent hypothesis exists. This makes it appropriate to apply the method only in the case where we have a guarantee that a consistent hypothesis can be found, something that is rarely possible in real applications. The same problem arises if we decide not to use a hypothesis unless its error is below a prespecified number.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/298300
- author
- Ambroladze, Amiran LU and Shawe-Taylor, J
- organization
- publishing date
- 2003
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Lecture Notes in Computer Science (Learning Theory and Kernel Machines)
- editor
- Schölkopf, Bernhard and Warmuth, Manfred K.
- volume
- 2777
- pages
- 729 - 730
- publisher
- Springer
- conference name
- 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003
- conference location
- Washington, DC, United States
- conference dates
- 2003-08-24 - 2003-08-27
- external identifiers
-
- wos:000185937100052
- scopus:9444240278
- ISSN
- 0302-9743
- 1611-3349
- ISBN
- 978-3-540-40720-1
- DOI
- 10.1007/b12006
- language
- English
- LU publication?
- yes
- id
- 2a34eefa-37e4-4c73-9868-c0dc5f639ebd (old id 298300)
- date added to LUP
- 2016-04-01 12:11:46
- date last changed
- 2024-01-08 11:47:19
@inproceedings{2a34eefa-37e4-4c73-9868-c0dc5f639ebd, abstract = {{The basic bound on the generalisation error of a PAC learner makes the assumption that a consistent hypothesis exists. This makes it appropriate to apply the method only in the case where we have a guarantee that a consistent hypothesis can be found, something that is rarely possible in real applications. The same problem arises if we decide not to use a hypothesis unless its error is below a prespecified number.}}, author = {{Ambroladze, Amiran and Shawe-Taylor, J}}, booktitle = {{Lecture Notes in Computer Science (Learning Theory and Kernel Machines)}}, editor = {{Schölkopf, Bernhard and Warmuth, Manfred K.}}, isbn = {{978-3-540-40720-1}}, issn = {{0302-9743}}, language = {{eng}}, pages = {{729--730}}, publisher = {{Springer}}, title = {{When is small beautiful?}}, url = {{http://dx.doi.org/10.1007/b12006}}, doi = {{10.1007/b12006}}, volume = {{2777}}, year = {{2003}}, }