Open access
Nov 2026
Online Decision Making with Local Differential Privacy
This paper designs LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings, and exploits the flexibility of stochastic gradient descent (SGD), whose theoretical guarantee for bandit problems is rarely explored.
Yuxuan Han, Zhi-Peng Liang, Yang Wang et al.
· Operational Research · 0 citations