Can I read FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits on EtoBox?

FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits by Chakraborty, Sunrit; Roy, Saptarshi; Basu, Debabrota is a scholarly article available to read on EtoBox.

What is FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits about?

High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems (e.g. personalized medicine), where high dimensional features (e.g. genomic data) on the users are available, but only a small subset of them are relevant. Motivated by data privacy concerns in these applications, we study the joint differentially private high dimensional sparse linear bandits, where both rewards and contexts are considered as private data. First, to quantify the cost of privacy, we derive a lower bound on the regret achievable in this setting. To further address the problem, we design a computationally efficient bandit algorithm, \textbf{F}orgetfu\textbf{L} \textbf{I}terative \textbf{P}rivate \textbf{HA}rd \textbf{T}hresholding (FLIPHAT). Along with doubling of episodes and episodic forgetting, FLIPHAT deploys a variant of Noisy Iterative Hard Thresholding (N-IHT) algorithm as a sparse linear regression oracle to ensure both privacy and regret-optimality. We show that FLIPHAT achieves optimal regret in terms of privacy parameters $\epsilon, \delta$, context dimension $d$, and time horizon $T$ up to a linear factor in model sparsity and logarithmic factor in $

Author

Chakraborty, Sunrit; Roy, Saptarshi; Basu, Debabrota

Published

2024

Language

EN