Please use this identifier to cite or link to this item:
https://doi.org/10.1006/jcss.2000.1741
DC Field | Value | |
---|---|---|
dc.title | Improved bounds on the sample complexity of learning | |
dc.contributor.author | Li, Y. | |
dc.contributor.author | Long, P.M. | |
dc.contributor.author | Srinivasan, A. | |
dc.date.accessioned | 2013-07-23T09:24:03Z | |
dc.date.available | 2013-07-23T09:24:03Z | |
dc.date.issued | 2001 | |
dc.identifier.citation | Li, Y., Long, P.M., Srinivasan, A. (2001). Improved bounds on the sample complexity of learning. Journal of Computer and System Sciences 62 (3) : 516-527. ScholarBank@NUS Repository. https://doi.org/10.1006/jcss.2000.1741 | |
dc.identifier.issn | 00220000 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/43067 | |
dc.description.abstract | We present a new general upper bound on the number of examples required to estimate all of the expectations of a set of random variables uniformly well. The quality of the estimates is measured using a variant of the relative error proposed by Haussler and Pollard. We also show that our bound is within a constant factor of the best possible. Our upper bound implies improved bounds on the sample complexity of learning according to Haussler's decision theoretic model. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1006/jcss.2000.1741 | |
dc.source | Scopus | |
dc.subject | Agnostic learning | |
dc.subject | Empirical process theory | |
dc.subject | Machine learning | |
dc.subject | PAC learning | |
dc.subject | Sample complexity | |
dc.type | Article | |
dc.contributor.department | MATERIALS SCIENCE | |
dc.contributor.department | COMPUTER SCIENCE | |
dc.description.doi | 10.1006/jcss.2000.1741 | |
dc.description.sourcetitle | Journal of Computer and System Sciences | |
dc.description.volume | 62 | |
dc.description.issue | 3 | |
dc.description.page | 516-527 | |
dc.description.coden | JCSSB | |
dc.identifier.isiut | 000168461300006 | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.