机器学习和理论经济学中的双层规划应用

2021.03.30

投稿:沈洁部门:管理学院浏览次数:

活动信息

时间: 2021年03月30日 14:30

地点: 上海大学校本部东区1号楼管理学院467室

 

题目:机器学习和理论经济学中的双层规划应用

演讲人:张进博士,南方科技大学

主持人:朱希德博士,上海大学管理学院

时间:2021330日,下午14:30

地点:上海大学校本部东区1号楼管理学院467

主办单位:上海大学管理学院、上海大学管理学院青年教师联谊会

 

演讲人简介:

    张进博士本科硕士均毕业于大连理工大学,博士毕业于加拿大维多利亚大学。20152018年间任职于香港浸会大学,2019年初加入南方科技大学。张进博士一直致力于优化理论和应用研究,主持多项国家级基金项目,代表性成果发表在Mathematical ProgrammingSIAM Journal on OptimizationSIAM Journal on Numerical AnalysisJournal of Machine Learning ResearchInternational Conference on Machine Learning等有重要影响力的运筹优化、机器学习期刊与会议上。张进博士的研究成果获得2020年第七届中国运筹学会青年科技奖,入选2021年深圳市优秀科技创新人才培养优秀青年计划。

 

演讲内容简介:

In this talk, we will discuss some recent advances in the applications of Bi-Level Programming Problem (BLPP). First, we study a gradient-based bi-level optimization method for learning tasks. In particular, by formulating bi-level models from the optimistic viewpoint and aggregating hierarchical objective information, we establish Bi-level Descent Aggregation (BDA), a flexible and modularized algorithmic framework for BLPP. Extensive experiments justify our theoretical results and demonstrate the superiority of the proposed BDA for different tasks, including hyper-parameter optimization and meta learning. Second, we propose a sufficient condition in the form of a partial error bound condition which guarantees the partial calmness condition. Our main result states that the partial error bound condition for the combined programs based on B and FJ conditions are generic for an important setting with applications in economics and hence the partial calmness for the combined program is not a particularly stringent assumption. Moreover we derive optimality conditions for the combined program for the generic case without any extra constraint qualifications.

 

欢迎广大师生参加!