您当前的位置:首页 >科学研究 > 学术交流

学术报告四十四:Ensemble learning: a multi-classifier framework for machine learning

来源:数学与统计学院     作者:     时间:2016/10/28 9:34:04  0次

数学与统计学院学术报告[2016] 044号

(高水平大学建设系列报告056号)

讲座题目: Ensemble learning: a multi-classifier framework    for machine learning

讲座人: ALAN WEE-CHUNG LIEW 

讲座时间:2016年11月1日 下午4:00-5:00 

讲座地点   科技楼514

报告内容:Many problems can be formulated as recovering a lowranktensor.Although an increasingly common task, tensor recovery remains a challenging problem because of the delicacy associated with the decomposition of higher order tensors. To overcome these difficulties, existing approaches often proceed by unfolding tensors into matrices and then apply techniques for matrix completion. We show here that such matricization fails to exploit the tensor structure and may lead to suboptimal procedure. More specically, we investigate a convex optimization approach to tensor completion by directly minimizing a tensor nuclear norm and prove that this leads to an improved sample size requirement. To establish our results, we develop a series of algebraic and probabilistic techniques such as characterization of subdieretial for tensor nuclear norm and concentration inequalities for tensor martingales, which may be of independent interests and could be useful in other tensor related problems. This is joint work with Ming Yuan.


报告人简历Dr. ALAN WEE-CHUNG LIEW is currently an Associate Professor with the School of Information & Communication Technology, Griffith University, Australia. His research interest is in the fields of medical imaging, computer vision, machine learning, pattern recognition, and bioinformatics.

He has published extensively in these areas and is the author of one book and more than 150 book chapters, journals and conference papers, and holds two international patents.  He has engaged actively in professional activities such as on the technical program committee and technical chair of many conferences, on several journal editorial boards (including IEEE Transactions on Fuzzy Systems), as assessor for Australian Research Council, HK Research Grant Council, and Austria Research Grant Council, and as reviewer for many international conferences and journals. He is a senior member of IEEE.

欢迎有兴趣的师生参加!

深圳大学统计科学研究所

深圳大学数学与统计学院

2016年10月28日

分享到: 0

数学与统计学院研究生工作奖励措施

2016年深圳大学数学与统计学院暨暑期夏令营招生指南