Anonymous Bandits for Multi-User Systems
Machine Learning
2022-10-25 v1
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 -anonymity constraint by requiring each observation to be an aggregation of rewards for at least 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
@article{arxiv.2210.12198,
title = {Anonymous Bandits for Multi-User Systems},
author = {Hossein Esfandiari and Vahab Mirrokni and Jon Schneider},
journal= {arXiv preprint arXiv:2210.12198},
year = {2022}
}