学术交流
学术交流
首页  >  学术科研  >  学术交流  >  正文

    Algorithmic Design for Wasserstein DRO Based Trustworthy Machine Learning

    2022-12-04  点击:[]


    伟德bevictor中文版

    创源大讲堂研究生学术讲座

    海 报


    讲座时间:2022126日星期二14:00-15:00

    讲座地点:腾讯会议:393 272 979;密码:1206

    主讲人简介:

    陈彩华,教授,南京大学理学博士,新加坡国立大学联合培养博士,主持/完成包括国家自然科学基金优秀青年项目在内的多项国家和省科研项目,代表作发表于Mathematical ProgrammingSIAM系列杂志, NeurIPSCVPR等国际知名学术期刊和会议。获华人数学家联盟最佳论文奖(20172018),中国运筹学会青年科技奖(2018),江苏省工业与应用数学学会青年奖(2020),南京大学青年五四奖章(2019),入选首批南京大学仲英青年学者(2017)、南京大学青年名师名课培育计划(2020)及江苏省社科优青(2019)

    讲座内容简介:

    Title: Algorithmic Design for Wasserstein DRO Based Trustworthy Machine Learning

    In this talk, we consider two essential features of the trustworthy machine learning—fairness and robustness. Mathematical optimization models based on Wasserstein DRO are then proposed to deal with the robust or/and fair machine learning problems. Taking advantage of their specific structure, we design several efficient stochastic algorithms to solve the resulted problems and also establish the corresponding convergence properties. Finally, a few of numerical experiments are presented to illustrating the efficiency of the algorithms.



    上一条:The Law of Importation in Mathematical Fuzzy Logics
    下一条:Variance Reduced Random Relaxed Projection Method for Constrained Finite-sum Minimization Problems

    关闭