Seminars

back Back to all Seminars

CS Seminar | Learning with Big Data by Incremental Optimization of Performance Measures

Start Date: December 1, 2015
End Date: December 1, 2015



 
By Professor Zhi-Hua Zhou
Department of Computer Science & Technology, Nanjing University, China
 


A popular approach to achieve a strong learning system is to take the performance measure that will be used for evaluation as an optimization target, and then accomplish the learning task by an optimization procedure. Many performance measures in machine learning, however, are unfortunately non-linear, non-smooth and non-convex, leading to difficult optimization problems. With big data, the optimization becomes even more challenging because of the concerns of computational, storage, communication costs, etc. Particularly, it becomes almost impossible to collect all data at first and then perform optimization, and it is desired to be able to optimize performance measures incrementally, without accessing the whole data. In this talk we will introduce some studies along this direction.
 
Biography: Zhi-Hua Zhou is a Professor and Founding director of the LAMDA Group. He is also the Standing Deputy Director of the National Key Lab for Novel Software Technology, Nanjing University. His research interests are mainly in artificial intelligence, machine learning and data mining. He authored the book "Ensemble Methods: Foundations and Algorithms", and published more than 100 papers in top-tier journals and conference proceedings. According to GoogleScholar, his works have received more than 18,000 citations, with an H-index of 66. He also holds 14 patents and has good experiences in applications. He has received various awards, including the National Natural Science Award of China, the IEEE CIS Outstanding Early Career Award, the Microsoft Professorship Award, etc. He serves as the Executive Editor-in-Chief of Frontiers of Computer Science, Associate Editor-in-Chief of Science China, and Associate Editor of the ACM TIST, IEEE TNNLS, etc. He is the founder of the ACML (Asian Conference on Machine Learning), Steering Committee member of PAKDD and PRICAI, and chair of various conferences. In this year he serves as Advisory Committee member and the machine learning track chair of IJCAI 2015, Program committee chair of ICDM 2015, etc. He is the chair of the IEEE CIS Data Mining and Big Data Analytics Technical Committee, the CCF Artificial Intelligence and Pattern Recognition Society, and the CAAI Machine Learning Society. He is an ACM Distinguished Scientist, IEEE Fellow, IAPR Fellow, IET/IEE Fellow and CCF Fellow.

More Information:

‚ÄčFor more info contact: Prof. Xiangliang Zhang; email: Xiangliang.Zhang@kaust.edu.sa
Date:  Tuesday 1st December   2015
Time: 12:00pm - 1:00pm
Location: Building 9, Lecture Hall II Room 2325
Light lunch will be available at 11:45 am