Most Correlated Arms Identification
Abstract
We study the problem of finding the most mutually correlated arms among many arms. We show that adaptive arms sampling strategies can have significant advantages over the non-adaptive uniform sampling strategy. Our proposed algorithms rely on a novel correlation estimator. The use of this accurate estimator allows us to get improved results for a wide range of problem instances.
Cite
Text
Liu and Bubeck. "Most Correlated Arms Identification." Annual Conference on Computational Learning Theory, 2014.Markdown
[Liu and Bubeck. "Most Correlated Arms Identification." Annual Conference on Computational Learning Theory, 2014.](https://mlanthology.org/colt/2014/liu2014colt-most/)BibTeX
@inproceedings{liu2014colt-most,
title = {{Most Correlated Arms Identification}},
author = {Liu, Che-Yu and Bubeck, Sébastien},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2014},
pages = {623-637},
url = {https://mlanthology.org/colt/2014/liu2014colt-most/}
}