Skip to main content

Adaptivity to Noise Parameters in Nonparametric Active Learning

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

To refer to this page use:
Abstract: This work addresses various open questions in the theory of active learning for nonparametric classification. Our contributions are both statistical and algorithmic: \beginitemize \item We establish new minimax-rates for active learning under common noise conditions. These rates display interesting transitions – due to the interaction between noise smoothness and margin – not present in the passive setting. Some such transitions were previously conjectured, but remained unconfirmed. \item We present a generic algorithmic strategy for adaptivity to unknown noise smoothness and margin; our strategy achieves optimal rates in many general situations; furthermore, unlike in previous work, we avoid the need for adaptive confidence sets, resulting in strictly milder distributional requirements.
Publication Date: 2017
Citation: Locatelli, Andrea, Alexandra Carpentier, and Samory Kpotufe. "Adaptivity to Noise Parameters in Nonparametric Active Learning." Proceedings of the 2017 Conference on Learning Theory, PMLR 65: pp. 1-34. 2017.
ISSN: 2640-3498
Pages: 1383 - 1416
Type of Material: Conference Article
Journal/Proceeding Title: Proceedings of the 2017 Conference on Learning Theory, PMLR
Version: Final published version. Article is made available in OAR by the publisher's permission or policy.

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