讲座主题：Unified Rules of Renewable Weighted Sums for Various Online Updating Estimations

主讲人： 林路教授 山东大学

讲座时间：2020年9月17日 16:00-18:00

参与方式：点击链接入会，或添加至会议列表：https://meeting.tencent.com/s/Ey6Wsa9WXsBR

会议 ID：579 587 369

会议直播: https://meeting.tencent.com/l/91lUnizS7Cbm

主讲人简介：

林路是山东大学金融研究院教授、博士生导师；在南开大学获得博士学位后，先在南开大学任教，然后到山东大学任教至今；从事大数据、高维统计、非参数和半参数统计以及金融统计等方的研究，在国际统计学、机器学习和相关应用学科顶级期刊(包括Annals of Statistics, Journal of Machine Learning Research,PLoS computational biology)和其它重要期刊发表研究论文110余篇；主持过多项国家自然科学基金课题、博士点专项基金课题、山东省自然科学基金重点项目等；获得国家统计局颁发的统计科技进步一等和二等奖(排名第一)，山东省优秀教学成果一等奖(排名第一)；是教育部应用统计专业硕士教育指导委员会成员，山东省政府参事。

讲座摘要：

We establish unified frameworks of renewable weighted sums (RWS) for various online updating estimations in the models with streaming data sets. The newly defined RWS lays the foundation ofonline updating likelihood, online updating loss function, online updating estimatingequation and so on. The idea of RWS is intuitive and heuristic, and the algorithm is computationally simple. This paper chooses nonparametric model as an exemplary setting. The RWS applies to various typesof nonparametric estimators, which include but are not limited to nonparametric likelihood, quasi-likelihood and least squares. Furthermore, the method and the theory can be extended into the models with both parameter and nonparametric function. The estimation consistency andasymptotic normality of the proposed renewable estimator are established, and the oracle property is obtained. Moreover, these properties are always satisfied, without any constraint on the number of data batches, which means that the new method is adaptive to the situation wherestreaming data sets arrive perpetually. The behavior of the method is further illustrated by various numericalexamples from simulation experiments and real data analysis.