標(biāo)題：Optimal Distributed Subsampling for Big Data Analysis
報(bào)告時(shí)間：2025年6月6日（星期五）13:30-14:30
報(bào)告地點(diǎn)：人民大街校區(qū)惟真樓523會(huì)議室
主講人： 艾明要
主辦單位：數(shù)學(xué)與統(tǒng)計(jì)學(xué)院
報(bào)告內(nèi)容簡(jiǎn)介：
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.
主講人簡(jiǎn)介：
艾明要，北京大學(xué)數(shù)學(xué)科學(xué)學(xué)院二級(jí)教授，北京大學(xué)教材建設(shè)博雅特聘教授。全國(guó)應(yīng)用統(tǒng)計(jì)專(zhuān)業(yè)學(xué)位研究生教育指導(dǎo)委員會(huì)委員、培養(yǎng)組組長(zhǎng)，中國(guó)現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)副理事長(zhǎng)，中國(guó)概率統(tǒng)計(jì)學(xué)會(huì)第十一屆理事會(huì)秘書(shū)長(zhǎng)，中國(guó)統(tǒng)計(jì)學(xué)會(huì)常務(wù)理事。擔(dān)任四個(gè)國(guó)際重要SCI期刊Stat Sinica、JSPI、SPL和Stat編委，國(guó)內(nèi)核心期刊 《系統(tǒng)科學(xué)與數(shù)學(xué)》、《數(shù)理統(tǒng)計(jì)與管理》、《數(shù)學(xué)進(jìn)展》編委，科學(xué)出版社《統(tǒng)計(jì)與數(shù)據(jù)科學(xué)叢書(shū)》編委。主要從事大數(shù)據(jù)采樣理論與算法、試驗(yàn)設(shè)計(jì)與分析、計(jì)算機(jī)仿真與建模、應(yīng)用統(tǒng)計(jì)的教學(xué)和研究工作，在AOS、JASA、Biometrika、《中國(guó)科學(xué)》等國(guó)內(nèi)外重要期刊發(fā)表學(xué)術(shù)論文八十余篇。主持國(guó)家自然科學(xué)基金重點(diǎn)項(xiàng)目1項(xiàng)（252萬(wàn)）、國(guó)際合作研究項(xiàng)目1項(xiàng)（200萬(wàn)）、重點(diǎn)項(xiàng)目子課題1項(xiàng)、面上項(xiàng)目5項(xiàng)，參與完成科技部重點(diǎn)研發(fā)計(jì)劃項(xiàng)目2項(xiàng)。兩次獲得北京大學(xué)優(yōu)秀博士學(xué)位論文指導(dǎo)教師，獲北京大學(xué)優(yōu)秀教學(xué)成果一等獎(jiǎng)、北京市高等學(xué)校優(yōu)秀教學(xué)成果二等獎(jiǎng)。
