报告时间：2020年12月5日（周六）上午9:30-10:30
会议地点：腾讯会议 ID：259 943 704
点击下面链接入会，或添加至会议列表： https://meeting.tencent.com/s/8GbF4R00h1hf
主讲人：陈迪荣教授
报告摘要： The constrained covariance (COCO) has been proposed for measuring dependence between random vectors. Kernel cross-covariance operators on reproducing kernel Hilbert spaces, as one of kernel methods of COCO which could extract nonlinear dependence, have attracted considerable attention. In this talk we consider learning rates of some estimators associated with kernel cross-covariance. For kernel cross-covariance operators, we bound a weighted summation of estimation errors of empirical singular functions by 16 times of the estimation error of empirical cross-covariance. It is much tighter than the classical result as the latter only bounds each error of singular function individually.
报告人简介：
陈迪荣，北京航空航天大学数学科学学院教授，北航“蓝天学者”特聘教授，博士生导师。主要研究方向为统计学习理论，小波分析与信息处理。1982年1月获学士学位，1992年7月获博士学位。先后主持国家自然科学基金8项，“863”课题3项，“973”计划子课题1项。发表SCI论文数十篇，其中多篇发表在权威刊物Appl. Comput. Harmonic Anal., Found. Comput. Math., IEEE Transaction on Automatic Control, IEEE Trans Information Theory和 Journal Machine Learning Research等上。单篇论文被SCI引用百余次。获教育部2012年度自然科学二等奖。
