Robust Learning from Discriminative Feature Feedback

Sanjoy Dasgupta, Sivan Sabato

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent work introduced the model of "learning from discriminative feature feedback", in which a human annotator not only provides labels of instances, but also identifies discriminative features that highlight important differences between pairs of instances. It was shown that such feedback can be conducive to learning, and makes it possible to efficiently learn some concept classes that would otherwise be intractable. However, these results all relied upon *perfect* annotator feedback. In this paper, we introduce a more realistic, *robust* version of the framework, in which the annotator is allowed to make mistakes. We show how such errors can be handled algorithmically, in both an adversarial and a stochastic setting. In particular, we derive regret bounds in both settings that, as in the case of a perfect annotator, are independent of the number of features. We show that this result cannot be obtained by a naive reduction from the robust setting to the non-robust setting.
Original languageEnglish GB
Title of host publicationProceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics
EditorsSilvia Chiappa, Roberto Calandra
PublisherPMLR
Pages973-982
Volume108
StatePublished - 2020

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR

Fingerprint

Dive into the research topics of 'Robust Learning from Discriminative Feature Feedback'. Together they form a unique fingerprint.

Cite this