澳门新葡8455最新网站,www.8455.com,新葡京最新官网

当前位置: 澳门新葡8455最新网站 > 学术活动 > 正文
Interaction Identification and Clique Screening for Classification with Ultra-high Dimensional Discrete Features
澳门新葡8455最新网站:2017年06月21日 14:09 点击数:

报告人:安百国

报告地点:澳门新葡8455最新网站4楼重点实验室报告厅

报告澳门新葡8455最新网站:2017年06月23日星期五10:00-11:00

邀请人:

报告摘要:

Interactions have greatly influenced recent scientific discoveries, but the identification of interactions is challenging in ultra-high dimensions. In this study, we propose an interaction identification method for classification with ultra-high-dimensional discrete features. We utilize clique sets to capture interactions among features, where features in a common clique have interactions that can be used for classification. The number of features related to the interaction is the size of the clique. Hence our method can consider interactions caused by more than two feature variables. We propose a Kullback-Leibler divergence-based approach to identify the clique sets correctly with a probability that tends to 1 as the sample size tends to infinity. A clique screening method is then proposed to filter out clique sets that are not useful for classification, and whose strong sure screening property can be guaranteed. Finally, a clique naive Bayes classifier is proposed for classification. Numerical studies demonstrate that our proposed approach performs very well.

主讲人概况:

安百国,首都经济贸易大学统计新葡京最新官网讲师,2012年博士毕业于澳门新葡8455最新网站,师从郭建华教授;2013-2015年先后在北卡罗来纳大学统计与运筹系、生物统计系进行博士后访问,2012-2016年在首都经济贸易大学统计新葡京最新官网做博士后工作,合作导师是纪宏教授。主要的研究兴趣包括回归压缩与选择、机器学习、超高维数据分析、文本挖掘和神经影像学分析等。

Copyright ©版权所有:澳门新葡8455最新网站

地址:吉林省长春市人民大街5268号|邮编:130024|电话:0431-85099589|传真:0431-85098237


XML 地图 | Sitemap 地图