Capped norm linear discriminant analysis and its applications
share
Classical linear discriminant analysis (LDA) is based on squared Frobenious norm and hence is sensitive to outliers and noise. To improve the robustness of LDA, in this paper, we introduce capped l_2,1-norm of a matrix, which employs non-squared l_2-norm and "capped" operation, and further propose a novel capped l_2,1-norm linear discriminant analysis, called CLDA. Due to the use of capped l_2,1-norm, CLDA can effectively remove extreme outliers and suppress the effect of noise data. In fact, CLDA can be also viewed as a weighted LDA. CLDA is solved through a series of generalized eigenvalue problems with theoretical convergency. The experimental results on an artificial data set, some UCI data sets and two image data sets demonstrate the effectiveness of CLDA.
READ FULL TEXT