学术报告 报告题目：Towards Understanding the Convergence Behavior of Newton-Type Methods for Structured Convex Optimization Problems
报 告 人：苏文藻 教授（香港中文大学）
报告时间：2017年03月16日（星期四）下午15:00-17:00
报告地点：4号楼4318室
欢迎广大师生前往！
数学学院
2017年03月13日
报告摘要：Recently, there has been a growing interest in applying Newton-type methods to solve structured
convex optimization problems that arise in machine learning and statistics. A major obstacle to the design
and analysis of such methods is that many problems of interest are neither strongly convex nor smooth. In this
talk, we will present some design techniques for overcoming such obstacle and report some recent progress
on analyzing the convergence rates of the resulting Newton-type methods using error bounds. We will also
discuss some directions for further study.