Open access
2025
Optimal Regret of Bandits under Differential Privacy
This work revisits the regret lower and upper bounds of ϵ -global DP bandits and proves a tighter regret lower bound involving a novel information-theoretic quantity characterising the hardness of ϵ -global DP in stochastic bandits.
Achraf Azize, Yulian Wu, Junya Honda et al.
· Neural Information Processin... · 0 citations