Anonymous Bandits for Multi-User Systems
Abstract
In this work, we present and study a new framework for online learning in systems with multiple users that provide user anonymity. Specifically, we extend the notion of bandits to obey the standard $k$-anonymity constraint by requiring each observation to be an aggregation of rewards for at least $k$ users. This provides a simple yet effective framework where one can learn a clustering of users in an online fashion without observing any user's individual decision. We initiate the study of anonymous bandits and provide the first sublinear regret algorithms and lower bounds for this setting.
Cite
Text
Esfandiari et al. "Anonymous Bandits for Multi-User Systems." Neural Information Processing Systems, 2022.Markdown
[Esfandiari et al. "Anonymous Bandits for Multi-User Systems." Neural Information Processing Systems, 2022.](https://mlanthology.org/neurips/2022/esfandiari2022neurips-anonymous/)BibTeX
@inproceedings{esfandiari2022neurips-anonymous,
title = {{Anonymous Bandits for Multi-User Systems}},
author = {Esfandiari, Hossein and Mirrokni, Vahab and Schneider, Jon},
booktitle = {Neural Information Processing Systems},
year = {2022},
url = {https://mlanthology.org/neurips/2022/esfandiari2022neurips-anonymous/}
}