Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/99195
DC FieldValue
dc.titleApproximating hyper-rectangles: Learning and pseudorandom sets
dc.contributor.authorAuer, P.
dc.contributor.authorLong, P.M.
dc.contributor.authorSrinivasan, A.
dc.date.accessioned2014-10-27T06:01:36Z
dc.date.available2014-10-27T06:01:36Z
dc.date.issued1998-12
dc.identifier.citationAuer, P.,Long, P.M.,Srinivasan, A. (1998-12). Approximating hyper-rectangles: Learning and pseudorandom sets. Journal of Computer and System Sciences 57 (3) : 376-388. ScholarBank@NUS Repository.
dc.identifier.issn00220000
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/99195
dc.description.abstractThe PAC learning of rectangles has been studied because they have been found experimentally to yield excellent hypotheses for several applied learning problems. Also, pseudorandom sets for rectangles have been actively studied recently because (i) they are a subproblem common to the derandomization of depth-2 (DNF) circuits and derandomizing randomized logspace, and (ii) they approximate the distribution of n independent multivalued random variables. We present improved upper bounds for a class of such problems of "approximating" high-dimensional rectangles that arise in PAC learning and pseudorandomness. © 1998 Academic Press.
dc.sourceScopus
dc.subjectApproximations of distributions
dc.subjectDerandomization
dc.subjectExplicit constructions
dc.subjectMachine learning
dc.subjectMultiple-instance learning
dc.subjectPAC learning
dc.subjectPseudorandomness
dc.subjectRamsey graphs
dc.subjectRandom graphs
dc.subjectRectangles
dc.subjectSample complexity
dc.typeArticle
dc.contributor.departmentINFORMATION SYSTEMS & COMPUTER SCIENCE
dc.description.sourcetitleJournal of Computer and System Sciences
dc.description.volume57
dc.description.issue3
dc.description.page376-388
dc.description.codenJCSSB
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

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

Page view(s)

103
checked on Jun 23, 2022

Google ScholarTM

Check


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