mg真人娱乐网站学术报告:Learning Theory of Distributed Kernel Regression

mg真人娱乐网站:管理员   时间:2018-05-31 点击数:



主讲人: 吴强副教授


Distributed learning provides effective tools for big data processing. An effective non-interactive approach for distributed learning is the divide and conquer method. It first partitions a big data set into multiple subsets, then a base algorithm is applied to each subset, and finally the results from these subsets are pooled together. In the context of nonlinear regression analysis, regularized kernel methods usually serve as efficient base algorithms for the second stage. In this talk, I will discuss the minimax optimality of several kernel based regression algorithms in distributed learning.



吴强博士的主要研究领域为统计模型与计算、机器学习、高维数据挖掘及应用,计算调和分析等。在Journal of Machine Learning Research, Applied and Computational Harmonic Analysis等国际权威期刊发表论文40余篇,出版专著“Classication and Regularization in Learning Theory”。特别在学习理论中的分类学习、基于系数正则化的学习、MEE学习等研究方向作出了标志性的研究成果,受到国内外学者的广泛关注。


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