上海财经大学 > 科学研究 > 学术交流 > 学术报告
  • 统计与管理学院2018年学术报告第34期

    【主 题】 Statistical Inference for Stochastic Approximation and Online Learning

    【报告人】 Weijie Su  助教授

    University of Pennsylvania

    【时 间】 2018年07月11日(星期三)16:00-17:00

    【地 点】 上海财经大学统计与管理学院大楼1208会议室

    摘 要】Stochastic gradient descent (SGD) is an immensely popular approach for online learning in settings where data arrives in a stream or data sizes are very large. However, despite an ever-increasing volume of works on SGD, much less is known about the statistical inferential properties of predictions based on SGD solutions. In this talk, we introduce a novel procedure termedHiGrad to conduct statistical inference for online learning, without incurring additional computational cost compared with the vanilla SGD. The HiGrad procedure begins by performing SGD iterations for a while and then split the single thread into a few, and this procedure hierarchically operates in this fashion along each thread. With predictions provided by multiple threads in place, a t-based confidence interval is constructed by decorrelating predictions using covariance structures given by the Ruppert–Polyak averaging scheme. Under certain regularity conditions, the HiGrad confidence interval is shown to attain asymptotically exact coverage probability. Finally, the performance of HiGrad is evaluated through extensive simulation studies and a real data example.

    嘉宾简介】Weijie Su is an Assistant Professor of Statistics at the Wharton School, University of Pennsylvania. Prior to joining Penn, he received his Ph.D. in Statistics from Stanford University in 2016 and his B.S. in Mathematics from Peking University in 2011. Su's research interests include machine learning, high-dimensional inference, multiple testing, and private data analysis.