Interactive Submodular Set Cover
Machine Learning
2010-05-24 v2
Abstract
We introduce a natural generalization of submodular set cover and exact active learning with a finite hypothesis class (query learning). We call this new problem interactive submodular set cover. Applications include advertising in social networks with hidden information. We give an approximation guarantee for a novel greedy algorithm and give a hardness of approximation result which matches up to constant factors. We also discuss negative results for simpler approaches and present encouraging early experimental results.
Keywords
Cite
@article{arxiv.1002.3345,
title = {Interactive Submodular Set Cover},
author = {Andrew Guillory and Jeff Bilmes},
journal= {arXiv preprint arXiv:1002.3345},
year = {2010}
}
Comments
15 pages, 1 figure