時 間：
瀏覽次數(shù)：4985
| 我要分享
主講人介紹：霍曉明教授現(xiàn)工作于佐治亞理工學(xué)院工業(yè)與系統(tǒng)工程專業(yè)的斯圖爾特學(xué)院，其主要研究研究領(lǐng)域為：Analytics and Big Data、Economic Decision Analysis、Statistics和Supply Chain Engineering。霍曉明教授已在Journal of the American
Statistical Association、Annals of Statistics、Statistica Sinica等國際頂級期刊發(fā)表數(shù)十篇文章。
?
講座內(nèi)容簡介：
This
talk will have two parts: Analytics and Statistics.
?
In
the first part, I will give an overview of business analytics, discuss its
research problems, as well as related research topics. I will review components
of business analytics that I perceive as critical. I will describe some
projects that I have done in the past, though they are not necessarily from
“business.” I will give my thoughts on how to carry out relevant research.
?
The
second part is about a particular statistical problem that I’ve worked on
recently, namely distributed inference. Distributed statistical inference has
recently attracted enormous attention. Many existing work focuses on the
averaging estimator. We propose a one-step approach to enhance a
simple-averaging based distributed estimator. We derive the corresponding asymptotic
properties of the newly proposed estimator. We find that the proposed one-step
estimator enjoys the same asymptotic properties as the centralized estimator.
The proposed one-step approach merely requires one additional round of
communication in relative to the averaging estimator; so the extra
communication burden is insignificant. In finite sample cases, numerical
examples show that the proposed estimator outperforms the simple averaging
estimator with a large margin in terms of the mean squared errors. A potential
application of the one-step approach is that one can use multiple machines to
speed up large scale statistical inference with little compromise in the
quality of estimators. The proposed method becomes more valuable when data can
only be available at distributed machines with limited communication bandwidth.
?
This
talk is based on joint work with Cheng Huang. A related manuscript can be found
at http://arxiv.org/abs/1511.01443.
