Differentially Private Best-Arm Identification

arXiv:2406.06408v1 Announce Type: cross
Abstract: Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical trials, tuning hyper-parameters, and conducting user studies. Motivated by the data privacy concerns invoked by these applications, we study the problem of BAI with fixed confidence in both the local and central models, i.e. $\epsilon$-local and $\epsilon$-global Differential Privacy (DP). First, to quantify the cost of privacy, we derive lower bounds on the sample complexity of any …

applications arm arxiv central cs.cr cs.lg data data privacy epsilon identification local math.st privacy privacy concerns private problem problems sensitive stat.ml stat.th studies study