Principal Component Analysis Based on L1Norm Maximization基于L1范数最大的主成分分析.pptVIP

Proof The projection vector is a linear combination of samples . It’s in the subspace spanned by . Then, we consider : * Form Greedy search algorithm. normal vector, (=1) Proof Because , is orthogonal to .. is orthogonal to . * The orthonormality of the projection vectors is guaranteed. Algorithms Even if the greedy search algorithm does not provide the optimal solution, it provides a set of good projections that maximize L1 dispersion. * Algorithms For data analysis, we could decide how much data could be captured. In PCA, we could compute the eigenvalue: * The eigenvalue is equivalent to the variance of the feature. We can compute the ratio of the variance to the total variance. The sum of variance: In eigenvalue, it exceeds 95% of the total variance, m is set to . Algorithms In PCA-L1, once is obtained, we can compute the variance of the feature. The sum of variance: The total variance: * We can set the appropriate number of extracted features like original PCA. Experiments In the experiments, we apply PCA-L1 algorithm and compared with R1-PCA and original PCA. Three experiments: A Toy problem with an Outlier UCI Data Sets Face Reconstruction * A Toy Problem with an Outlier Consider the data points in a 2D space: If we discard the outlier, the projection vector should be . * an outlier. A Toy Problem with an Outlier The projection vector: * outlier A Toy Problem with an Outlier The residual error : * outlier Average residual error PCA-L1 L2-PCA R1-PCA 1.200 1.401 1.206 Much influenced by the outlier. UCI Data Sets Data sets in UCI machine learning repositories. Compare the classification performances. 1-NN classifier was used and 10-fold cross validation for average classification rate. For PCA-L1, we set the initial projection vector as