@incollection{mlsys2020_136,
 abstract = {Contextual bandit algorithms\textasciitilde (CBAs) often rely on personal data to provide recommendations. Centralized CBA agents utilize potentially sensitive data from recent interactions to provide personalization to end-users. Keeping the sensitive data locally, by running a local agent on the user\textquotesingle s device, protects the user\textquotesingle s privacy, however, the agent requires longer to produce useful recommendations, as it does not leverage feedback from other users.

This paper proposes a technique we call Privacy-Preserving Bandits (P2B); a system that updates local agents by collecting feedback from other local agents in a differentially-private manner. Comparisons of our proposed approach with a non-private, as well as a fully-private (local) system, show competitive performance on both synthetic benchmarks and real-world data. Specifically, we observed only a decrease of 2.6\% and 3.6\% in multi-label classification accuracy, and a CTR increase of 0.0025 in online advertising for a privacy budget \epsilon  \approx  0.693. These results suggest P2B is an effective approach to challenges arising in on-device privacy-preserving personalization. },
 author = {Malekzadeh, Mohammad and Athanasakis, Dimitrios  and Haddadi, Hamed and Livshits, Ben},
 booktitle = {Proceedings of Machine Learning and Systems 2020},
 pages = {350--362},
 title = {Privacy-Preserving Bandits},
 year = {2020}
}