Hyper Parameters Optimization for Gaussian Mechanism with Coyote-Badger and Kriging Model for EHR

Abstract

Differential privacy (DP) is a cornerstone of privacy-preserving data analysis.  Among its mechanisms, the Gaussian mechanism stands out for its ability to provide robust privacy guarantees by adding Gaussian noise to computations. However, the mechanism’s hyper parameters, including the noise scale (σ) and privacy budget (ϵ), require careful optimization to balance privacy and utility. This paper explores the application of Coyote Optimization Algorithm (COA) and Badger Optimization Algorithm (BOA) for hyper- parameter optimization, coupled with the Kriging surrogate model to enhance computational efficiency. Comparative evaluations demonstrate that these methods outperform traditional approaches, achieving better convergence rates and improved privacy-utility trade-offs.