报告题目：Classification in Imbalanced Complex Longitudinal Data

报告时间：2021年12月13日 下午14:30-17:30

报告地点：腾讯会议731248168

报告摘要：Imbalanced classification has drawn considerable attention in the statistics and machine learning literature. Typically, traditional classification methods, such as logistic regression and support vector machine (SVM), often perform poorly when a severely skewed class distribution is observed, not to mention under a high-dimensional longitudinal data structure. Given the ubiquity of big data in areas including modern health research, face recognition, and object identification, it is expected that imbalanced classification may encounter an additional level of difficulty that is imposed by such a complex data structure.

In this talk, we propose a nonparametric classification approach for binary imbalanced data in longitudinal and high-dimensional settings. Technically, the functional principal component analysis (FPCA) is applied for feature extraction under the sparse and irregular longitudinal structure. The univariate exponential loss function coupled with group LASSO penalty is then adopted into the classification procedure in high-dimensional settings. Along with the improvement in AUC and sensitivity for imbalanced classification, our approach also provides a meaningful feature selection for interpretation while enjoying a remarkable computational efficiency. The proposed method is illustrated with the real data of Alzheimer’s disease and Pima Indians diabetes, and its empirical performance in finite sample size is extensively evaluated by simulations.

报告人简介：宋卫星，男，博士，美国堪萨斯州立大学统计系教授兼研究生项目主任，博士生导师。1999年在中国科学院系统科学研究所获第一个博士学位，1999-2001在北京师范大学数学系做博士后，2006年在美国密歇根州立大学获得第二个博士学位。曾在香港大学精算与统计系和美国罗切斯特大学生物统计系做访问学者。主要从事测量误差模型、非参数与半参数模型中的统计推断，高维数据分析与大数据建模，稳健性估计研究。主持或参与多项自然基金项目和联合项目的研究工作，目前主持一项美国国家自然科学基金项目。担任国际十几种主要统计学期刊的长期审稿人。