LocallyDifferentiallyPrivate (Contextual)Bandits Learning

Further, we extend our(ε,δ)-LDP algorithm toGeneralized Linear Bandits,which enjoysa sub-linear regret O(T3/4/ε) and is conjectured to be nearly optimal. Note that given the existingΩ(T) lower bound for DP contextual linear bandits [35], our result shows afundamental difference between LDP and DP contextual bandits learning.