The widespread proliferation of data-driven decision-making has ushered in a recent interest in the design of privacy-preserving algorithms. In this paper, we consider the ubiquitous problem of gaussian process (GP) bandit optimization from the lens of privacy-preserving statistics. We propose a solution for differentially private GP bandit optimization that combines a uniform kernel approximator with random perturbations, providing a generic framework to create differentially-private (DP) Gaussian process bandit algorithms. For two specific DP settings - joint and local differential privacy, we provide algorithms based on efficient quadrature Fourier feature approximators, that are computationally efficient and provably no-regret for popular stationary kernel functions. Our algorithms maintain differential privacy throughout the optimization procedure and critically do not rely explicitly on the sample path for prediction, making the parameters straightforward to release as well.
翻译:数据驱动决策的广泛扩散最近引起了对隐私保护算法设计的兴趣。 在本文中,我们从隐私保护统计的角度来考虑普通的保单过程(GP)土匪优化问题。 我们提出一个有差别的私人强盗优化解决方案,将统一的内核对齐器和随机扰动器结合起来,提供一个通用框架来创建有区别的私有(DP)高斯进程土匪算法。 对于两种特定的DP设置 — — 联合和本地差异隐私,我们提供基于高效的四维地物特征对称等器的算法,这种算法既有效,又对普通的定点内核功能来说是完全无差别的。我们的算法在整个优化程序中保持了有差别的隐私,并且严格地说,我们并不明确依赖抽样路径来进行预测,使参数能够直接释放。