Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/99486
DC Field | Value | |
---|---|---|
dc.title | Complexity of learning according to two models of a drifting environment | |
dc.contributor.author | Long, Philip M. | |
dc.date.accessioned | 2014-10-27T06:04:37Z | |
dc.date.available | 2014-10-27T06:04:37Z | |
dc.date.issued | 1998 | |
dc.identifier.citation | Long, Philip M. (1998). Complexity of learning according to two models of a drifting environment. Proceedings of the Annual ACM Conference on Computational Learning Theory : 116-125. ScholarBank@NUS Repository. | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/99486 | |
dc.description.abstract | The problem of learning functions from some set X to {0, 1} using two models of a drifting environment is studied. It is shown that a bound on the rate of drift of the distribution generating the examples is sufficient for learning to relative accuracy; this matches a known necessary condition to within a constant factor. A sufficient condition is established for the realizable case, also matching a known necessary condition to within a constant factor. A relatively simple proof of a bound of on the sample complexity of agnostic learning in a fixed environment is presented. | |
dc.source | Scopus | |
dc.type | Conference Paper | |
dc.contributor.department | INFORMATION SYSTEMS & COMPUTER SCIENCE | |
dc.description.sourcetitle | Proceedings of the Annual ACM Conference on Computational Learning Theory | |
dc.description.page | 116-125 | |
dc.description.coden | 215 | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.