Structural query-by-committee
Machine Learning
2018-03-20 v1 Machine Learning
Abstract
In this work, we describe a framework that unifies many different interactive learning tasks. We present a generalization of the {\it query-by-committee} active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically and empirically, with and without noise.
Cite
@article{arxiv.1803.06586,
title = {Structural query-by-committee},
author = {Christopher Tosh and Sanjoy Dasgupta},
journal= {arXiv preprint arXiv:1803.06586},
year = {2018}
}