Multi-Armed Bandits with Local Differential Privacy
It addresses privacy concerns in online services like recommendations for users, but is incremental as it builds on existing bandit and privacy frameworks.
The paper tackles the problem of minimizing regret in multi-armed bandit systems while ensuring local differential privacy to protect user data, achieving algorithms with regret bounds that match proven lower bounds up to constant factors.
This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee. In stochastic bandit systems, the rewards may refer to the users' activities, which may involve private information and the users may not want the agent to know. However, in many cases, the agent needs to know these activities to provide better services such as recommendations and news feeds. To handle this dilemma, we adopt differential privacy and study the regret upper and lower bounds for MAB algorithms with a given LDP guarantee. In this paper, we prove a lower bound and propose algorithms whose regret upper bounds match the lower bound up to constant factors. Numerical experiments also confirm our conclusions.