大會演講

講者介紹：

Chih-Jen Lin is currently a distinguished professor at the Department of Computer Science, National Taiwan University. He obtained his B.S. degree from National Taiwan University in 1993 and Ph.D. degree from University of Michigan in 1998. His major research areas include machine learning, data mining, and numerical optimization. He is best known for his work on support vector machines (SVM) for data classification. His software LIBSVM is one of the most widely used and cited SVM packages. For his research work he has received many awards, including best paper awards in some top computer science conferences. He is an IEEE fellow, a AAAI fellow, and an ACM fellow for his contribution to machine learning algorithms and software design. More information about him can be found at http://www.csie.ntu.edu.tw/~cjlin.

演講摘要：

Optimization plays an important role in many machine learning methods, but significant differences between the two areas exist. These differences have caused difficulties for applied mathematicians (including those working on numerical optimization) to make real impact on machine learning. In this talk I will humbly share some past experiences in working on both areas. Through the discussion of empirical risk minimization that covers from simple linear classification to complicated deep neural networks, we will see that incorporating properties of machine learning problems is essential in designing useful optimization methods.