报告地点：行健楼学术活动室505
邀请人：徐玲玲副教授
报告摘要：In this talk, several stochastic versions on the alternating direction method of multipliers and the Peaceman-Rachford splitting method are presented for a class of structured convex optimization problems whose objective function is the sum of a possibly nonsmooth convex function and an average function of many smooth convex functions. We show the main convergence results of these methods and their performance on testing the popular empirical risk minimization problem in supervised learning and the 3D CT reconstruction problem in medical imaging, respectively. Finally, several interesting questions are shared and discussed.
报告人简介：白建超，博士 (后)，西北工业大学数学与统计学院副教授，硕士生导师。他博士毕业于西安交通大学，师从李继成教授和张洪超教授；主要从事机器学习和统计学习等领域的大规模优化方法、理论与应用研究，在CSIAM Transactions on Applied Mathematics、IEEE Transactions on Medical Imaging、Computational Optimization and Applications、Journal of Computational and Applied Mathematics、Numerical Linear Algebra with Applications等期刊上发表SCI论文20余篇；主研科技部重点研发计划项目、国家自然科学基金青年项目、中国博士后科学基金项目等；现担任CSIAM大数据与人工智能专委会委员、陕西省运筹学会理事、陕西省科协人才奖励评审专家和西安市科技计划项目会评专家。
