报告题目：在线差分隐私推断

主讲嘉宾：谢锦瀚 副教授

时间：2026年4月9日下午16:00      

地点：格物楼3103室

摘要：In this talk, we present a general privacy-preserving optimization-based framework for statistical inference in real-time environments. We first consider online settings in which observations arrive sequentially, and develop a noisy stochastic gradient descent algorithm under local differential privacy. We then introduce an online federated learning framework including synchronous and asynchronous scenarios, where data remain distributed across clients and are generated over time. Our proposed algorithms are one-pass, depending only on the current data and the previous estimate, which effectively reduces both time and space complexity. To construct private confidence intervals efficiently in an online manner, two methods are proposed: private plug-in and random scaling. We also establish the convergence rates and functional central limit theorems for the proposed estimators, providing a theoretical foundation for our online inference tools. Numerical experiments demonstrate the finite-sample performance of our proposed procedures, underscoring the efficacy and reliability.

嘉宾介绍：谢锦瀚，2019年博士毕业于云南大学，先后在香港中文大学、加拿大阿尔伯塔大学、美国北卡罗来纳大学教堂山分校从事博士后研究工作。主要从事大规模复杂数据分析和统计机器学习。

初审｜韩芳宇

复审｜鲁学伟

终审｜杨汉春