主题：Large-scale multiple testing of cross-covariance functions with applications to functional network models
主讲人：蒋庆 北京师范大学
主持人：王国长 暨南大学
时间：2025年3月24日（周一）上午10:30-11:30
地点：暨南大学石牌校区经济学院大楼（中惠楼）102室
摘要
The estimation of functional networks through functional covariance and graphical models have recently attracted increasing attention in settings with high dimensionalfunctional data, where the number of functional variables p is comparable to, and maybe larger than, the number of subjects. However, the existing methods all dependon regularization techniques, which make it unclear how the involved tuningparameters are related to the number of false edges. In this paper, we first reframethe functional covariance model estimation as a tuning-free problem ofsimultaneouslytesting p(p-1)/2 hypotheses for cross-covariance functions, and introduce a novelmultiple testing procedure. We also explore the multiple testing procedure under ageneralerror-contamination framework and establish that our procedure can controlfalse discoveries asymptotically. We then demonstrate that our proposed methodsfor two concrete examples: the functional covariance model for discretely observedfunctional data and the more important-yet-challenging functional graphical model, can be seamlessly integrated into the general error-contamination framework, and, with verifiable conditions, achieve theoretical guarantees on effective false discoverycontrol. Finally, we showcase the superiority of our proposals through extensive simulationsand brain connectivity analysis of two neuroimaging datasets.
主讲人简介
蒋庆，北京师范大学文理学院统计系特聘副研究员，2019年博士毕业于北京师范大学。主要研究方向包括高维数据分析、模型检验和函数型数据分析。主持国家自然科学基金青年科学基金项目一项，参与多项国家级项目，研究成果发表在JASA, JOE和JMVA等学术期刊上。
欢迎感兴趣的师生参加!
校对| 王国长
责编| 彭毅
初审| 姜云卢
终审发布| 何凌云
（来源：暨南大学经济学院微信公众号）
