Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition

• 成果类型: Article; Early Access
• 署名作者: Wang, Hua; Gao, Sheng; Zhang, Huanyu; Shen, Milan; Su, Weijie; Wu, Jiayuan
• 署名单位: University of Pennsylvania
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459; 1537-274X
• DOI: 10.1080/01621459.2026.2668139
• 发表日期: 2026-06-20
• 关键词: Differential Privacy; Edgeworth Expansion; Privacy accounting; f-differential privacy

摘要

In privacy-preserving data analysis, many procedures and algorithms are structured as compositions of multiple private building blocks. As such, an important question is how to efficiently compute the overall privacy loss under composition. This article introduces the Edgeworth Accountant, an analytical approach to composing differential privacy guarantees for private algorithms. Leveraging the f-differential privacy framework (Dong, Roth, and Su), the Edgeworth Accountant accurately tracks privacy loss under composition, enabling a closed-form expression of privacy guarantees through privacy-loss log-likelihood ratios (PLLRs). As implied by its name, this method applies the Edgeworth expansion to estimate and define the probability distribution of the sum of the PLLRs. Furthermore, by using a technique that simplifies complex distributions into simpler ones, we demonstrate the Edgeworth Accountant's applicability to any noise-addition mechanism. Its main advantage is providing (epsilon, delta)-differential privacy bounds that are non-asymptotic and do not significantly increase computational cost. This feature sets it apart from previous approaches, in which the running time increases with the number of mechanisms under composition. We conclude by showing how our Edgeworth Accountant offers accurate estimates and tight upper and lower bounds on (epsilon, delta)-differential privacy guarantees, especially tailored for training private models in deep learning and federated analytics. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.