大连理工大学数学科学学院
通知与公告

【北京大学】Optimal Distributed Subsampling Techniques for Big Data Analysis

2022年04月11日 09:02  点击:[]

报告题目: Optimal Distributed Subsampling Techniques for Big Data Analysis

报告人:   艾明要 教授北京大学

报告时间: 2022413日(星期10:00-11:00

报告地点: 腾讯会议(ID755 176 621 

校内联系人:牛一 副教授    联系电话:84708351-8081

 

报告摘要: Subsampling methods are effective techniques to reduce computational burden and maintain statistical inference efficiency for big data. In this talk, we will review different subsampling techniques for different models from linear model, to generalized linear model, and to estimation equations. If the data volume is so large that nonuniform subsampling probabilities cannot be calculated all at once, subsampling with replacement is infeasible to implement. This problem is solved by using a new subsampling without replacement, called Poisson subsampling. To deal with the situation that the full data are stored in different blocks or at multiple locations, a distributed subsampling framework is developed, in which statistics are computed simultaneously on smaller partitions of the full data. Finally, the proposed strategies are illustrated and evaluated through numerical experiments on both simulated and real data sets.

 

报告人简介:艾明要,北京大学数学科学学院统计学教授、博士生导师。兼任全国应用统计专业学位研究生教育指导委员会委员,中国现场统计研究会第十一届理事会副理事长,试验设计分会理事长,高维数据统计分会副理事长,中国数学会第十三届理事会理事,中国概率统计学会秘书长,中国数学会均匀设计分会副主任等。担任4国际重要SCI期刊Statistica SinicaJSPISPLStat的副主编,国内核心期刊 《系统科学与数学》、《数理统计与管理》编委,科学出版社《统计与数据科学丛书》编委。主要从事大数据采样技术、试验设计与分析、应用统计等的教学和研究工作,在AoSJASABiometrika中国科学》等国内外重要期刊发表学术论文七十余篇。主持国家自然科学基金重点项目“大数据采样技术”1项,主持国家自然科学基金面上项目6项,参与完成科技部重点研发计划(973)项目2项。

上一条:【东华大学】Existence and upper semicontinuity of time-dependent attractors for the non-autonomous nonlocal diffusion equations 下一条:【天津大学】Unimodal Sequences in the Theory of Partitions

关闭