File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Efficient semi-supervised and active learning of disjunctions

TitleEfficient semi-supervised and active learning of disjunctions
Authors
Issue Date2013
Citation
30th International Conference on Machine Learning, ICML 2013, 2013, n. PART 1, p. 633-641 How to Cite?
AbstractWe provide efficient algorithms for learning disjunctions in the semi-supervised setting under a natural regularity assumption introduced by (Balcan & Blum, 2005). We prove bounds on the sample complexity of our algorithms under a mild restriction on the data distribution. We also give an active learning algorithm with improved sample complexity and extend all our algorithms to the random classification noise setting. Copyright 2013 by the author(s).
Persistent Identifierhttp://hdl.handle.net/10722/341150

 

DC FieldValueLanguage
dc.contributor.authorBalcan, Maria Florina-
dc.contributor.authorBerlind, Christopher-
dc.contributor.authorEhrlich, Steven-
dc.contributor.authorLiang, Yingyu-
dc.date.accessioned2024-03-13T08:40:34Z-
dc.date.available2024-03-13T08:40:34Z-
dc.date.issued2013-
dc.identifier.citation30th International Conference on Machine Learning, ICML 2013, 2013, n. PART 1, p. 633-641-
dc.identifier.urihttp://hdl.handle.net/10722/341150-
dc.description.abstractWe provide efficient algorithms for learning disjunctions in the semi-supervised setting under a natural regularity assumption introduced by (Balcan & Blum, 2005). We prove bounds on the sample complexity of our algorithms under a mild restriction on the data distribution. We also give an active learning algorithm with improved sample complexity and extend all our algorithms to the random classification noise setting. Copyright 2013 by the author(s).-
dc.languageeng-
dc.relation.ispartof30th International Conference on Machine Learning, ICML 2013-
dc.titleEfficient semi-supervised and active learning of disjunctions-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.scopuseid_2-s2.0-84897483120-
dc.identifier.issuePART 1-
dc.identifier.spage633-
dc.identifier.epage641-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats