On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence

by   Achraf Azize, et al.

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 to name a few. Motivated by the data privacy concerns invoked by these applications, we study the problem of BAI with fixed confidence under ϵ-global Differential Privacy (DP). First, to quantify the cost of privacy, we derive a lower bound on the sample complexity of any δ-correct BAI algorithm satisfying ϵ-global DP. Our lower bound suggests the existence of two privacy regimes depending on the privacy budget ϵ. In the high-privacy regime (small ϵ), the hardness depends on a coupled effect of privacy and a novel information-theoretic quantity, called the Total Variation Characteristic Time. In the low-privacy regime (large ϵ), the sample complexity lower bound reduces to the classical non-private lower bound. Second, we propose AdaP-TT, an ϵ-global DP variant of the Top Two algorithm. AdaP-TT runs in arm-dependent adaptive episodes and adds Laplace noise to ensure a good privacy-utility trade-off. We derive an asymptotic upper bound on the sample complexity of AdaP-TT that matches with the lower bound up to multiplicative constants in the high-privacy regime. Finally, we provide an experimental analysis of AdaP-TT that validates our theoretical results.


When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits

We study the problem of multi-armed bandits with ϵ-global Differential P...

Tight Bounds for Differentially Private Anonymized Histograms

In this note, we consider the problem of differentially privately (DP) c...

Private and polynomial time algorithms for learning Gaussians and beyond

We present a fairly general framework for reducing (ε, δ) differentially...

Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification

We study the problem of the identification of m arms with largest means ...

Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples

We study the problem of estimating mixtures of Gaussians under the const...

PAC Security: Automatic Privacy Measurement and Control of Data Processing

We propose and study a new privacy definition, termed Probably Approxima...

Non-Asymptotic Analysis of a UCB-based Top Two Algorithm

A Top Two sampling rule for bandit identification is a method which sele...

Please sign up or login with your details

Forgot password? Click here to reset