Loading web-font TeX/Caligraphic/Regular
Cascading Bandit Under Differential Privacy | IEEE Conference Publication | IEEE Xplore

Cascading Bandit Under Differential Privacy


Abstract:

This paper studies differential privacy (DP) and local differential privacy (LDP) in cascading bandits. Under DP, we propose a UCB-based algorithm which guarantees ϵ-indi...Show More

Abstract:

This paper studies differential privacy (DP) and local differential privacy (LDP) in cascading bandits. Under DP, we propose a UCB-based algorithm which guarantees ϵ-indistinguishability and a regret of \mathcal{O}\left( {{{\left( {\frac{{\log T}}{ \in }} \right)}^{1 + \xi }}} \right) for an arbitrarily small ξ. This result significantly improves O\left( {\frac{{{{\log }^3}T}}{ \in }} \right) in the previous work. Under (ϵ, δ)-LDP, we relax the K2 dependence through the tradeoff between privacy budget ϵ and error probability δ, and obtain a regret of {\text{ }}\mathcal{O}{\text{ }}\left( {\frac{{K\log (1/\delta )\log T}}{{{ \in ^2}}}} \right), where K is the size of the arm subset. This result holds for both Gaussian mechanism and Laplace mechanism by analyses on the composition. Extensive experiments corroborate our theoretic findings.
Date of Conference: 23-27 May 2022
Date Added to IEEE Xplore: 27 April 2022
ISBN Information:

ISSN Information:

Conference Location: Singapore, Singapore
Shanghai Jiao Tong University
University of Michigan
The Chinese University of Hong Kong, Shenzhen
Shanghai Jiao Tong University

Shanghai Jiao Tong University
University of Michigan
The Chinese University of Hong Kong, Shenzhen
Shanghai Jiao Tong University

Contact IEEE to Subscribe

References

References is not available for this document.