讲座题目:Regression Analysis of Reciprocity in Directed Networks
主讲人:冷琛雷 教授
主持人:谌自奇 研究员
开始时间:2026-04-21 15:00
讲座地址:普陀校区理科大楼A1514
主办单位:统计学院
报告人简介:
Chenlei Leng is Chair Professor of Statistics and Machine Learning in the Department of Applied Mathematics at the Hong Kong Polytechnic University. His research focuses on developing novel statistical and machine learning methodologies for large and complex data, with an emphasis on high-dimensional, correlated, and network-structured data. A Fellow of the Institute of Mathematical Statistics and an Elected Member of the International Statistical Institute, Professor Leng has held several notable leadership roles, including Chair of the Research Section of the Royal Statistical Society, Co-Director of the Oxford–Warwick Centre for Doctoral Training, and as an inaugural Turing Fellow at the Alan Turing Institute.
报告内容:
互惠性(reciprocity)——即个体之间形成相互连接的倾向——是许多有向网络中的一种基本结构特征。尽管这一现象普遍存在,但在统计网络模型中,互惠性尚未得到充分整合,尤其是在与协变量信息的结合方面。本文提出了 R2-Model,这是一种新颖且灵活的框架,能够在引入协变量效应的同时,对互惠性进行显式建模。该框架建立在广义 p1 模型之上,能够同时刻画网络的稀疏性和节点异质性,并提供了迄今为止对互惠性最为全面的参数化方式——不仅能够捕捉其基准水平,还能够刻画其如何随观测协变量发生系统性变化。针对高维性和干扰参数带来的挑战,我们提出了一种条件似然估计方法,用于分离并一致估计互惠性效应。我们还建立了其理论性质,包括一致性、渐近正态性,以及在广泛稀疏性条件下的极小极大最优性。大量模拟实验和真实数据应用表明,R2-Model 具有良好的灵活性、可解释性以及优异的有限样本表现,突出了其在揭示有向网络中由协变量驱动的互惠性模式方面的实际应用价值。

