Interactive Structure Learning with Structural Query-by-Committee

Christopher Tosh; Sanjoy Dasgupta

NeurIPS 2018spotlight8 citations

Interactive Structure Learning with Structural Query-by-Committee

Abstract

In this work, we introduce interactive structure learning, a framework that unifies many different interactive learning tasks. We present a generalization of the 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.

BibTeX

@inproceedings{NEURIPS2018_08c5433a,
 author = {Tosh, Christopher and Dasgupta, Sanjoy},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Interactive Structure Learning with Structural Query-by-Committee},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/08c5433a60135c32e34f46a71175850c-Paper.pdf},
 volume = {31},
 year = {2018}
}