Southwest Jiaotong University School of Mathematics

信息与计算科学系

首页  >  学术科研  >  信息与计算科学系  >  正文

学术报告:Lower-order regularization method for group sparse optimization with applications

来源:信息与计算科学系   作者:信息与计算科学系     日期:2018-09-26 13:34:48   点击数:  

报告题目:Lower-order regularization method for group sparse optimization with applications

报告时间:201892814:00-15:00

报告地点:X2511

报告人:胡耀华 博士


摘要: The lower-order regularization problem has been widely studied for finding sparse solutions of linear inverse problems and gained successful applications in various mathematics and applied science fields. In this talk, we will present the lower-order regularization method for (group) sparse optimization problem in three aspects: theory, algorithm and application. In the theoretical aspect, by introducing a notion of restricted eigenvalue condition, we will establish an oracle property and a global recovery bound for the lower-order regularization problem. In the algorithmic aspect, we will apply the well-known proximal gradient method to solve the lower-order regularization problem, and establish its linear convergence rate under a simple assumption. In the aspect of application, we apply the lower-order group sparse regularization method to solve two important problems in systems biology: gene transcriptional regulation and cell fate conversion.

报告人简介:

胡耀华,深圳大学数学与统计学院副教授(香港理工大学博士,师从杨晓琪教授),主要从事最优化理论、算法和应用研究,特别专注于稀疏优化及其应用,主持国家自然科学基金2项,省市级科研项目4项。2015年获“深圳市海外高层次人才”荣誉称号,2016年获“广东省计算数学优秀青年论文特等奖”,2017年荣获深圳市南山区“领航人才”称号。在SIAM Journal on Optimization,Inverse Problems,Journal of Machine Learning Research, European Journal of Operational Research,BMC Genomics等国际期刊上发表二十篇学术论文,参与开发多个生物信息学工具包/网页服务器。