暨南经院学术系列活动之统计学系列Seminar第91期:夏冬(香港科技大学)

发布者:彭毅发布时间:2021-12-28浏览次数:439

  主题Statistical Inferences of Linear Forms for Noisy Matrix Completion

  主讲人:夏冬(香港科技大学)

  主持人:杨广仁(太阳城集团)

  会议时间20211229日(周三)上午10:00-11:00

  会议工具:腾讯会议(ID494-919-989


  We introduce a flexible framework for making inferences about general linear forms of a large matrix based on noisy observations of a subset of its entries. In particular, under mild regularity conditions, we develop a universal procedure to construct asymptotically normal estimators of its linear forms through double-sample debiasing and low-rank projection whenever an entry-wise consistent estimator of the matrix is available. These estimators allow us to subsequently construct confidence intervals for and test hypotheses about the linear forms. Our proposal was motivated by a careful perturbation analysis of the empirical singular spaces under the noisy matrix completion model which might be of independent interest.

 

主讲人简介

  夏冬博士,香港科技大学数学系助理教授,2016年在佐治亚理工获得博士学位,分别在哥伦比亚大学做博士后和威斯康星大学麦迪逊分校做访问助理教授。夏博士的研究领域为高维统计,机器学习和优化理论。夏博士分别在 AoS, JRSSB  JMLR 等统计和机器学习领域顶尖期刊发表学术成果,目前担任JSPI的副主编。