

Seminar on Probability Theory and Mathematical Statistics
July 16, 2018 15:30–17:30, St. Petersburg, PDMI, room 311 (nab. r. Fontanki, 27)






Statistical Inference With HighDimensional Data
CunHui Zhang^{}, ^{} 
Number of views: 
This page:  94 

Abstract:
We consider statistical inference in a semilowdimensional approach to the analysis of highdimensional data. The relationship between this semilowdimensional approach and regularized estimation of highdimensional objects is parallel to the more familiar one between semiparametric analysis and nonparametric estimation. Lowdimensional projection methods are used to correct the bias of regularized highdimensional estimators, leading to efficient point and interval estimation. Bootstrap can be used to carry out simultaneous inference. Only a small fraction of labelled data are needed in a semisupervised setting. Examples include regression and graphical models for continuous and binary data.
Language: English

