程昆博士学术报告

发布时间:2019年11月04日 作者:王小捷   消息来源:    阅读次数:[]

报告题目: An Introduction to Functional Data Analysis
报告时间:2019年11月4日 15:00-17:00
报告地点:数学院一楼145报告厅
报告摘要:Functional data analysis (FDA) has gained increasing importance in modern data analysis due to the improved capability to record and store a vast amount of data and advances in scientific computing. In this talk, we give a brief introduction to FDA, including Functional PCA, Functional CCA and Functional Linear Regression. Besides, we introduce a wavelet-based approach to mean and covariance estimate for sparse functional data. The procedures are shown to be adaptive in aid of block thresholding rules. We also derive the L^2 convergence rates of the proposed estimators. In particular, the mean estimator attains the minimax optimality.
报告人简介:程昆,2016年毕业于中南大学数学科学班,保研至北京航空航天大学,专业为统计学。研究方向包括:函数型数据分析、统计学习理论以及非参统计方法。



打印】【收藏】 【关闭