论文标题
从Rashomon集合进行差异化抽样，以及凸出优化的Langevin扩散的普遍性
Differentially Private Sampling from Rashomon Sets, and the Universality of Langevin Diffusion for Convex Optimization
论文作者
论文摘要
在本文中，我们提供了一个基于langevin扩散（LD）及其相应的离散化的算法框架，使我们能够同时获得：i）一种用于从指数机制中进行取样的算法，其隐私分析不取决于始终的机制，并且在任何时间都不能依赖于任何时间，而无需保密而无与伦比，并且ii and sigranity and Is and Ii＆II）且ii）且ii）stristir and Ii）strip and II）。直接结果，我们在纯和近似差异隐私（DP）下（强烈）（强烈）凸出的（强烈）凸出损失的最佳过剩经验和人口风险保证。该框架使我们能够从Rashomon集合设计DP统一采样器。 Rashomon集被广泛用于可解释和强大的机器学习，了解可变的重要性以及表征公平性。
In this paper we provide an algorithmic framework based on Langevin diffusion (LD) and its corresponding discretizations that allow us to simultaneously obtain: i) An algorithm for sampling from the exponential mechanism, whose privacy analysis does not depend on convexity and which can be stopped at anytime without compromising privacy, and ii) tight uniform stability guarantees for the exponential mechanism. As a direct consequence, we obtain optimal excess empirical and population risk guarantees for (strongly) convex losses under both pure and approximate differential privacy (DP). The framework allows us to design a DP uniform sampler from the Rashomon set. Rashomon sets are widely used in interpretable and robust machine learning, understanding variable importance, and characterizing fairness.
