首师大高端统计论坛

报告题目：高维尺度不变的判别分析

报告人：郑术蓉 教授（东北师范大学）

摘要：We   propose a scale invariant linear discriminant analysis classifier for   high-dimensional data with dense signals. The method is valid for both cases that the data dimension is smaller   or greater than the sample size. Based   on recent advances of the sample correlation matrix in random matrix theory,   we derive the asymptotic limits of the error rate which characterizes the   influences of the data dimension and the tuning parameter. The major   advantage of our proposed classifier is scale invariant and it is applicable to any variances of   the feature. Several numerical studies are investigated and our proposed classifier performs   favorably in comparison to some existing methods.

报告人简介：郑术蓉，东北师范大学教授。主要从事大维随机矩阵理论及高维统计分析的研究。曾在Annals of Statistics, JASA, Biometrika等统计学重要学术期刊上发表多篇学术论文。现任Annals of Statistics、Statistica Sinica等学术期刊编委，曾主持多项国家自然科学基金项目等。

时间：2023年1月5日（周四）下午15：00

线上参加：#腾讯会议 523-3915-6716

联系人：周洁

举办单位：威斯尼斯人5158cc、交叉科学学院、北京国家应用数学中心