Skip to yearly menu bar Skip to main content


Poster

Diameter-Based Active Learning

Christopher Tosh · Sanjoy Dasgupta

Gallery #145

Abstract:

To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.

Live content is unavailable. Log in and register to view live content