NeurIPS 2017poster29 citations
A KL-LUCB algorithm for Large-Scale Crowdsourcing
Ervin Tanczos, Robert Nowak, Bob Mankoff
Abstract
This paper focuses on best-arm identification in multi-armed bandits with bounded rewards. We develop an algorithm that is a fusion of lil-UCB and KL-LUCB, offering the best qualities of the two algorithms in one method. This is achieved by proving a novel anytime confidence bound for the mean of bounded distributions, which is the analogue of the LIL-type bounds recently developed for sub-Gaussian distributions. We corroborate our theoretical results with numerical experiments based on the New Yorker Cartoon Caption Contest.
BibTeX
@inproceedings{NIPS2017_c02f9de3,
author = {Tanczos, Ervin and Nowak, Robert and Mankoff, Bob},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {A KL-LUCB algorithm for Large-Scale Crowdsourcing},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/c02f9de3c2f3040751818aacc7f60b74-Paper.pdf},
volume = {30},
year = {2017}
}