Poster
Agnostic Active Learning Without Constraints
Alina Beygelzimer · Daniel Hsu · John Langford · Tong Zhang

Mon Dec 6th 12:00 -- 12:00 AM @ None #None

We present and analyze an agnostic active learning algorithm that works without keeping a version space. This is unlike all previous approaches where a restricted set of candidate hypotheses is maintained throughout learning, and only hypotheses from this set are ever returned. By avoiding this version space approach, our algorithm sheds the computational burden and brittleness associated with maintaining version spaces, yet still allows for substantial improvements over supervised learning for classification.

Author Information

Alina Beygelzimer (Yahoo Labs)
Daniel Hsu (Columbia University)
John Langford
Tong Zhang (Tencent)

More from the Same Authors