报告时间：6月6日 9:40

报告地点：雁归楼A4 3016

报告题目：Nonconvex truncated conditional value at risk-based sparse linear regression

摘要：

Conditional value at risk (CVaR) is a widely recognized risk measure used to manage data uncertainty within risk management. In this paper, we study a class of sparse linear regression models based on truncated CVaR measure and L0-norm regularization. Due to the nonconvexity and nonsmoothness of the objective functions, as well as the NP-hardness of the problem with the L0-norm regularization, we propose an approximation model that employs a tight relaxation of the L0-norm. The solution equivalence between the proposed model and its approximation model is explored. To efficiently solve the approximation model, we develop a semismooth Newton-based proximal majorization-minimization algorithm. Furthermore, the convergence analysis of the proposed algorithm is presented, and the convergence rate for the reduced CVaR-based sparse linear regression model is established. Moreover, extensive numerical experiments conducted on both synthetic and real datasets validate the stability and effectiveness of the proposed algorithm, demonstrating significant improvements in both sparsity and accuracy compared to existing state-of-the-art methods.

报告人简介：

李敏，南京大学工程管理学院教授、博士生导师。2002年、2007年在南京大学数学系获得理学学士与博士学位，曾在东南大学经济管理学院任教。曾入选高校“青蓝工程”优秀青年骨干教师培养对象、江苏省“333高层次人才培养工程”中青年学术技术带头人、教育部新世纪优秀人才支持计划、江苏社科优青等。目前担任江苏省运筹学会理事、管理科学与工程学会理事等。主要研究领域是最优化理论与方法及其在管理科学上的应用，学术论文发表在Mathematical Programming、Mathematics of Operations Research、SIAM Journal on Optimization、NIPS、Naval Research Logistics、European Journal of Operational Research等。近年来主持了包括国家自然科学基金、江苏省社会科学基金重点项目、江苏省自然科学基金等课题。