The Label Complexity of Active Learning from Observational Data
Abstract
Counterfactual learning from observational data involves learning a classifier on an entire population based on data that is observed conditioned on a selection policy. This work considers this problem in an active setting, where the learner additionally has access to unlabeled examples and can choose to get a subset of these labeled by an oracle. Prior work on this problem uses disagreementbased active learning, along with an importance weighted loss estimator to account for counterfactuals, which leads to a high label complexity. We show how to instead incorporate a more efficient counterfactual risk minimizer into the active learning algorithm. This requires us to modify both the counterfactual risk to make it amenable to active learning, as well as the active learning process to make it amenable to the risk. We provably demonstrate that the result of this is an algorithm which is statistically consistent as well as more labelefficient than prior work.
 Publication:

arXiv eprints
 Pub Date:
 May 2019
 DOI:
 10.48550/arXiv.1905.12791
 arXiv:
 arXiv:1905.12791
 Bibcode:
 2019arXiv190512791Y
 Keywords:

 Statistics  Machine Learning;
 Computer Science  Machine Learning
 EPrint:
 NeurIPS 2019