报告时间:2024年4月25日(周四)10:00-11:30
报告地点:崇德西楼815报告厅
报告主题一:Private Estimation and Inference in High Dimensional Regression with FDR Control
报告摘要：
In this talk, we present new methods for conducting practical differentially private (DP) estimation and inference in high-dimensional linear regression. We start by proposing a differentially private Bayesian Information Criterion for selecting the unknown sparsity parameter in DP-sparse linear regression, eliminating the need for prior knowledge of model sparsity, a requisite in the existing literature. Then we propose a differentially private debiased algorithm that enables privacy-preserving inference on a particular subset of regression parameters. We also introduce a differentially private multiple testing procedure that controls the false discovery rate (FDR). This allows for accurate and privacy-preserving identification of significant predictors in the regression model.
作者简介：
李赛，中国人民大学统计与大数据研究院准聘副教授，博士生导师。2018年于罗格斯新泽西州立大学获得统计博士学位，毕业后于宾夕法尼亚大学生物统计系和统计系进行博士后研究，目前的研究方向包括高维数据分析、迁移学习、因果推断的统计方法及理论和在遗传学、流行病学和机器学习中的应用。
报告主题二:Two-Level Nonregular Fractional Factorial Designs
报告摘要：
Fractional factorial designs can be divided into regular designs and nonregular designs. The regular design has a simple structure, while the run size is limited to a power of 2. The nonregular design has a complex structure, but it enjoys flexible run size and can be used to estimate more effects. As a special kind of nonregular design, the parallel flats design has received more and more attention. The regular designs are also called single flat, and the designs composed of several single flats from the same family are called parallel flats designs. Parallel flats designs (PFDs) consisting of three parallel flats (3-PFDs) are the most frequently utilized PFDs, due to their simple structure. Generalizing to f-PFD with f>3 is more challenging. This paper aims to study the general theory for the f-PFD for any f≥3. We propose a method for obtaining the confounding frequency vectors for all nonequivalent f-PFDs, and to find the least G-aberration (or highest D-efficiency) f-PFD constructed from any single flat. PFDs are particularly useful for constructing nonregular fraction, split-plot or randomized block designs. We also characterize the quaternary code design series as PFDs. Finally, we show how designs constructed by concatenating regular fractions from different families may also have a parallel flats structure.
作者简介：
王春燕，中国人民大学统计学院讲师，南开大学博士，田纳西大学访问学者，普渡大学博士后助理研究员。研究方向包括统计试验设计、计算机试验、次序添加试验等。相关文章发表在《中国科学 数学》、《Annals of Statistics》、 《Statistica Sinica》等期刊上。
