首页 工院讲座学术讲座-Trace Lasso Regularization for Adaptive Sparse Canonical Correlation Analysis with Applications

学术讲座-Trace Lasso Regularization for Adaptive Sparse Canonical Correlation Analysis with Applications

举办单位:信息科学与工程学院

讲座题目

Trace Lasso Regularization for Adaptive Sparse   Canonical Correlation Analysis with Applications

讲 座 人

彭拯

讲座人

职称、职务

教授

主持人

许弘雷

讲座类型

R自然科学

讲座对象

全校师生

举办时间

2018/1/12 13:00

□社会科学

举办地点

福建省汽车电子与电驱动技术重点实验室会议室

彭拯,现为福州大学数学与计算机科学学院教授,博士生导师,当前主持国家自然科学基金一项。

June   2008: Ph. D., Department of Mathematics, Shanghai University
   June 2003: M.Sc., Department of Mathematics, Hunan Normal University
   June 1991: B.Sc., Department of Mathematics, YueYang Normal College
   June. 1998: B.Sc., Department of Computer   Science, Xiangtan University

讲座

主要内容

By adapting the trace Lasso and Lasso   regularization, an adaptive sparse version of CCA (adaptive SCCA for short)   is proposed. The adaptive SCCA reduces the instability of the estimator when   covariates are highly correlated, and thus improves their   interpretation.  The adaptive SCCA   model is reformulated to an orthogonality constrained optimization problem,   and an effective splitting method is proposed for solving the resulting   problem, The performance of the proposed SCCA model is compared with other   sparse CCA techniques in different simulation settings, and the validity is   also illustrated on the real genomic data sets.