学术交流
学术交流
首页  >  学术科研  >  学术交流  >  正文

    【学术讲座】Machine Learning Meets PDEs

    2023-07-04  点击:[]

    报告人:Yulong Lu ( Assistant Professor, University of Massachusetts Amherst)

    研究领域:应用分析,应用概率与统计

    报告时间:2023/07/06 10:00-11:00

    报告地点:https://meeting.tencent.com/dm/peZiod03tVgw

    #腾讯会议:485-226-080 会议密码:307060

    报告题目:Machine Learning Meets PDEs

    :Machine learning have recently been used to design innovative, and arguably revolutionary methods for solving many challenging problems from science and engineering which are modeled by partial differential equations (PDEs). Conversely, PDEs provide an important set of tools for understanding machine learning methods. This talk devotes to presenting some recent progress at the interface between neural networks-based machine learning and PDEs.

    In the first part of the talk, we will discuss theoretical analysis of neural-network methods for solving high dimensional PDEs. We show that Deep Ritz solvers achieve dimension-free generalization rates in solving elliptic problems under the assumption that the solutions belong to Barron spaces. To justify such assumption, we develop new complexity-based solution theory for several elliptic problems in the Barron spaces.

    In the second part of the talk, we will showcase the power of PDEs in minimax optimization, which underpins a variety of problems in adversarial machine learning. More precisely, we consider the problem of finding the mixed Nash equilibria (MNE) in two-player zero sum games on the space of probability measures. It is proved that two-scale gradient descent ascent (GDA) dynamics converges to the unique MNE of an entropy-regularized objective at an exponential rate. We also show that an annealed GDA with a logarithmically decaying cooling schedule converges to the MNE of the original unregularized objective.

     

    上一条:【学术讲座】Improved decodings for low rank parity check codes
    下一条:分形几何青年研讨会会议安排

    关闭

Baidu
sogou