香港盒宝典资料大全

学术海报

学术海报

    数学科学学院学术报告:Distributed Learning for Handling Big Data(基于大数据的分布式学习)

    日期:2017-06-16来源:数学科学学院 浏览量:

    报告题目:Distributed Learning for Handling Big Data基于大数据的分布式学习

    报告时间:2017619 日(周一)上午10:00

    报告地点:7JC306

    主讲人:周定轩教授,香港城市大学

    报告摘要:Analyzing and processing big data has been an important and challenging task in various fields of science and technology. Distributed learning provides powerful methods for handling big data and forms an important topic in learning theory. It is based on a divide-and-conquer approach and consists of three steps: first we divide oversized data into subsets and each data subset is distributed to one individual machine, then each machine processes the distributed data subset to produce one output, finally the outputs from individual machines are combined to generate an output of the distributed learning algorithm. It is expected that a distributed learning algorithm can perform as efficiently as one big machine which could process the whole oversized data, in addition to the advantages of reducing storage and computing costs. This talk describes mathematical analysis of distributed learning.

    报告人简介

    周定轩,香港城市大学讲座教授。主要研究方向: 学习理论, 数据科学, 逼近论, 小波分析;为国际学习理论研究的领导者之一。

        1988年本科, 1991年博士毕业于浙江大学。19922月到19932月在中科院数学所,博士后;19932月到19957月在德国做洪堡学者及客座教授;19957月到199611月在加拿大Alberta大学做博士后。199611月起就职于香港城市大学数学系,20099月起担任讲座教授。2005年获国家杰出青年基金, 2014-2016年被Thomson Reuters列为Highly-cited Researcher

        曾任香港城市大学数学系系主任, 香港数学学会副会长。现为香港研究资助局(RGC)理科组专家成员, 浙江大学竺可桢学院香港院友会会长, SCI杂志Analysis and Applications主编, Applied and Computational Harmonic Analysis, Journal of Approximation TheoryComplex Analysis and Operator Theory, Journal of Computational Analysis and Analysis, 高校应用数学学报编委。