Regularized Kernel Algorithms for Support Estimation

[摘要] In the framework of non-parametric support estimation, we study the statistical properties of an estimator defined by means of Kernel Principal Component Analysis (KPCA). In the context of anomaly/novelty detection the algorithm was first introduced by Hoffmann in 2007. We also extend to above analysis to a larger class of set estimators defined in terms of a filter function.

[学科分类] 数学（综合）

[关键词] Support estimation;Kernel PCA;novelty detection;Dimensionality reduction.;Regularized kernel methods