Please use this identifier to cite or link to this item: https://doi.org/10.1023/A:1007666507971
DC FieldValue
dc.titleComplexity of learning according to two models of a drifting environment
dc.contributor.authorLong, P.M.
dc.date.accessioned2013-07-04T07:34:57Z
dc.date.available2013-07-04T07:34:57Z
dc.date.issued1999
dc.identifier.citationLong, P.M. (1999). Complexity of learning according to two models of a drifting environment. Machine Learning 37 (3) : 337-354. ScholarBank@NUS Repository. https://doi.org/10.1023/A:1007666507971
dc.identifier.issn08856125
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/39144
dc.description.abstractWe show that a cε3/VC dim(F) bound on the rate of drift of the distribution generating the examples is sufficient for agnostic learning to relative accuracy ε, where c>0 is a constant; this matches a known necessary condition to within a constant factor. We establish a cε2/VC dim (F) sufficient condition for the realizable case, also matching a known necessary condition to within a constant factor . We provide a relatively simple proof of a bound of O(1/ε2(VC dim (F)+log 1/δ)) on the sample complexity of agnostic learning in a fixed environment.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1023/A:1007666507971
dc.sourceScopus
dc.typeArticle
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1023/A:1007666507971
dc.description.sourcetitleMachine Learning
dc.description.volume37
dc.description.issue3
dc.description.page337-354
dc.description.codenMALEE
dc.identifier.isiut000083963600005
Appears in Collections:Staff Publications

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

Google ScholarTM

Check

Altmetric


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