Timezone: »

Beyond Disagreement-Based Agnostic Active Learning
Chicheng Zhang · Kamalika Chaudhuri

Wed Dec 10 04:00 PM -- 08:59 PM (PST) @ Level 2, room 210D

We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The main algorithms for this problem are {\em{disagreement-based active learning}}, which has a high label requirement, and {\em{margin-based active learning}}, which only applies to fairly restricted settings. A major challenge is to find an algorithm which achieves better label complexity, is consistent in an agnostic setting, and applies to general classification problems. In this paper, we provide such an algorithm. Our solution is based on two novel contributions -- a reduction from consistent active learning to confidence-rated prediction with guaranteed error, and a novel confidence-rated predictor.

Author Information

Chicheng Zhang (Microsoft Research)
Kamalika Chaudhuri (UCSD)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors