Timezone: »

 
Poster
Adaptive Region-Based Active Learning
Corinna Cortes · Giulia DeSalvo · Claudio Gentile · Mehryar Mohri · Ningshan Zhang

Thu Jul 16 06:00 AM -- 06:45 AM & Thu Jul 16 06:00 PM -- 06:45 PM (PDT) @
in Poster Session 41 »

We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, while actively requesting labels. We prove theoretical guarantees for both the generalization error and the label complexity of our algorithm, and analyze the number of regions defined by the algorithm under some mild assumptions. We also report the results of an extensive suite of experiments on several real-world datasets demonstrating substantial empirical benefits over existing single-region and non-adaptive region-based active learning baselines.

Keywords: Active Learning · Online Learning, Active Learning, and Bandits

Author Information

Corinna Cortes (Google Research)
Giulia DeSalvo (Google Research)
Claudio Gentile (Google Research)
Mehryar Mohri (Google Research and Courant Institute of Mathematical Sciences)
Ningshan Zhang (Hudson River Trading)

More from the Same Authors