Learning from discriminative feature feedback

Sanjoy Dasgupta, Akansha Dey, Nicholas Roberts, Sivan Sabato

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

1 Scopus citations


We consider the problem of learning a multi-class classifier from labels as well as simple explanations that we call discriminative features. We show that such explanations can be provided whenever the target concept is a decision tree, or can be expressed as a particular type of multi-class DNF formula. We present an efficient online algorithm for learning from such feedback and we give tight bounds on the number of mistakes made during the learning process. These bounds depend only on the representation size of the target concept and not on the overall number of available features, which could be infinite. We also demonstrate the learning procedure experimentally.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
Number of pages9
StatePublished - 2018
Externally publishedYes
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: 2 Dec 20188 Dec 2018


Conference32nd Conference on Neural Information Processing Systems, NeurIPS 2018


Dive into the research topics of 'Learning from discriminative feature feedback'. Together they form a unique fingerprint.

Cite this