mg真人娱乐网站学术报告:Distributed Learning for Handling Big Data(基于大数据的分布式学习)

mg真人娱乐网站:管理员   时间:2017-06-16 点击数:

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




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.



1988年本科, 1991年博士毕业于浙江大学。1992年2月到1993年2月在中科院数学所,博士后;1993年2月到1995年7月在德国做洪堡学者及客座教授;1995年7月到1996年11月在加拿大Alberta大学做博士后。1996年11月起就职于香港城市大学数学系,2009年9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 Theory,Complex Analysis and Operator Theory, Journal of Computational Analysis and Analysis,高校应用数学学报编委。

Copyright ©版权所有:mg真人娱乐网站

地址:济南市市中区南辛庄西路336号mg真人娱乐网站西校区第七教学楼   邮编:250022   电话(传真):0531-82767313

XML 地图 | Sitemap 地图