报告问题 (Title):High dimensional PCA(高维主因素剖析)
报告人 (Speaker): 潘灼烁 教授(随机矩阵领域着名专家,,,,南洋理工大学)
报告时间 (Time):2021年11月5日(周五) 9:00
报告所在 (Place):腾讯聚会(聚会号:958 938 143)
约请人(Inviter):张阳春
主理部分:理学院数学系
报告摘要:We propose an approach based on sample eigenvalues of sample covariance matrices to estimate the number of significant components in high dimensional data. We show the consistency of the estimator in different type of data. Simulations are run to compare the performance with those existed approaches.