当前位置 : 首页 > 学术报告 学术报告

哥伦比亚大学李根教授学术报告预告

信息来源: 曲阜师范大学 发布日期: 2016-07-06浏览次数:

哥伦比亚大学李根教授学术报告预告

报告题目:Dimension Reduction in Big Data

报告人:李根  哥伦比亚大学公共卫生学院生物统计系

时间:201677 17:00-18:00

地点:数学楼报告厅

 

AbstractBig data become increasingly common in various areas, posing a great challenge to statistics. Dimension reduction is a useful tool that facilitates further statistical analysis. However, standard dimension reduction methods only apply to a single data set, and do not easily accommodate special features of data, such as functionality, sparsity, and multi-modality. In this talk, I will introduce a new supervised dimension reduction framework. The framework builds upon principal component analysis (PCA), but is adapted to deal with modern data types. In particular, it can flexibly account for any auxiliary information in the reduction of a primary data matrix, incorporate variable selection and smoothing, and jointly decompose multiple related data sets when applicable. I will demonstrate the advantage of the proposed methods using examples from bioinformatics and business analytics.

 

李根教授简介:现任哥伦比亚大学公共卫生学院生物统计系助理教授、博士生导师,兼任博士生招生委员会委员,博士生资格考试委员会委员。2013年暑期曾于美国贝尔实验室实习,2014年秋季在德州农工大学进行学术访问。曾获国际生物计量学协会会议杰出文章奖、数理统计协会优秀论文奖、北卡罗莱纳大学教学奖、学术奖等。主要从事高维数据分析、函数型数据分析、生物统计等方面的教学和研究,参与一项世界级合作项目,多项国家级科研项目,在ScienceJournal of Multivariate AnalysisJournal of Computational and Graphical Statistics等知名杂志发表多篇学术论文。