Academic Lectures:Fast algorithms for large scale generalized distance weighted discrimination
发布时间: 2016-05-27 访问次数: 94

ReportTitle:Fast algorithms for large scale generalized distance weighted discrimination

Reporter(Institution):Pro. Defeng Sun(NationalUniversityof Singapore),30th May, 2016
Location:B-201, Building of Economics & Management, JiulonghuCampus

High dimension low sample size statistical analysis is important in a wide range of applications. In such situations, the highly appealing discrimination method, support vector machine, can be improved to alleviate data piling at the margin. This leads naturally to the development of distance weighted discrimination (DWD), which can be modeled as a second-order cone programming problem and solved by interior-point methods when the scale (in sample size and feature dimension) of the data is moderate. Here, we design a scalable and robust algorithm for solving large scale generalized DWD problems. Numerical experiments on real data sets from the UCI repository demonstrate that our algorithm is highly efficient in solving large scale problems, and sometimes even more efficient than the highly optimized LIBSVM for solving the corresponding SVM problems. [This is a joint work with Xin Yee Lam, J. S. Marron and Kim-Chuan Toh]