Rodriguez-Lujan, Irene; Huerta, Ramon; Elkan, Charles; Santa Cruz, Carlos Quadratic programming feature selection. (English) Zbl 1242.68245 J. Mach. Learn. Res. 11, 1491-1516 (2010). Summary: Identifying a subset of features that preserves classification accuracy is a problem of growing importance, because of the increasing size and dimensionality of real-world data sets. We propose a new feature selection method, named quadratic programming feature selection (QPFS), that reduces the task to a quadratic optimization problem. In order to limit the computational complexity of solving the optimization problem, QPFS uses the Nyström method for approximate matrix diagonalization. QPFS is thus capable of dealing with very large data sets, for which the use of other methods is computationally expensive. In experiments with small and medium data sets, the QPFS method leads to classification accuracy similar to that of other successful techniques. For large data sets, QPFS is superior in terms of computational efficiency. Cited in 10 Documents MSC: 68T05 Learning and adaptive systems in artificial intelligence 90C20 Quadratic programming 62H30 Classification and discrimination; cluster analysis (statistical aspects) Keywords:feature selection; quadratic programming; Nyström method; large data set; highdimensional data PDFBibTeX XMLCite \textit{I. Rodriguez-Lujan} et al., J. Mach. Learn. Res. 11, 1491--1516 (2010; Zbl 1242.68245) Full Text: Link