Interactive and Concentrated Differential Privacy for Bandits. (arXiv:2309.00557v1 [stat.ML])

Bandits play a crucial role in interactive learning schemes and modern
recommender systems. However, these systems often rely on sensitive user data,
making privacy a critical concern. This paper investigates privacy in bandits
with a trusted centralized decision-maker through the lens of interactive
Differential Privacy (DP). While bandits under pure $\epsilon$-global DP have
been well-studied, we contribute to the understanding of bandits under zero
Concentrated DP (zCDP). We provide minimax and problem-dependent lower bounds
on regret for finite-armed and linear …

critical data decision differential privacy global lens making play privacy recommender systems role sensitive systems under user data