Online Active Model Selection for Pre-trained Classifiers
Machine Learning
2021-04-20 v3 Machine Learning
Abstract
Given pre-trained classifiers and a stream of unlabeled data examples, how can we actively decide when to query a label so that we can distinguish the best model from the rest while making a small number of queries? Answering this question has a profound impact on a range of practical scenarios. In this work, we design an online selective sampling approach that actively selects informative examples to label and outputs the best model with high probability at any round. Our algorithm can be used for online prediction tasks for both adversarial and stochastic streams. We establish several theoretical guarantees for our algorithm and extensively demonstrate its effectiveness in our experimental studies.
Cite
@article{arxiv.2010.09818,
title = {Online Active Model Selection for Pre-trained Classifiers},
author = {Mohammad Reza Karimi and Nezihe Merve Gürel and Bojan Karlaš and Johannes Rausch and Ce Zhang and Andreas Krause},
journal= {arXiv preprint arXiv:2010.09818},
year = {2021}
}