Skip to main content

An Adaptive Strategy for Active Learning with Smooth Decision Boundary

Author(s): Locatelli, Andrea; Carpentier, Alexandra; Kpotufe, Samory

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1pc31
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLocatelli, Andrea-
dc.contributor.authorCarpentier, Alexandra-
dc.contributor.authorKpotufe, Samory-
dc.date.accessioned2021-10-11T14:17:10Z-
dc.date.available2021-10-11T14:17:10Z-
dc.date.issued2018en_US
dc.identifier.citationLocatelli, Andrea, Alexandra Carpentier, and Samory Kpotufe. "An Adaptive Strategy for Active Learning with Smooth Decision Boundary." In Proceedings of Algorithmic Learning Theory, PMLR 83, pp. 547-571. 2018.en_US
dc.identifier.issn2640-3498-
dc.identifier.urihttp://proceedings.mlr.press/v83/locatelli18a.html-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1pc31-
dc.description.abstractWe present the first adaptive strategy for active learning in the setting of classification with smooth decision boundary. The problem of adaptivity (to unknown distributional parameters) has remained opened since the seminal work of Castro and Nowak (2007), which first established (active learning) rates for this setting. While some recent advances on this problem establish \emph{adaptive} rates in the case of univariate data, adaptivity in the more practical setting of multivariate data has so far remained elusive. Combining insights from various recent works, we show that, for the multivariate case, a careful reduction to univariate-adaptive strategies yield near-optimal rates without prior knowledge of distributional parameters.en_US
dc.format.extent547 - 571en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings of Algorithmic Learning Theory, PMLRen_US
dc.rightsFinal published version. Article is made available in OAR by the publisher's permission or policy.en_US
dc.titleAn Adaptive Strategy for Active Learning with Smooth Decision Boundaryen_US
dc.typeConference Articleen_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/journal-articleen_US

Files in This Item:
File Description SizeFormat 
ActiveLearnSmoothDecisionBoundary.pdf656.53 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.