Feature selection in weakly coherent matrices

04/03/2018
by   Stéphane Chrétien, et al.
0

A problem of paramount importance in both pure (Restricted Invertibility problem) and applied mathematics (Feature extraction) is the one of selecting a submatrix of a given matrix, such that this submatrix has its smallest singular value above a specified level. Such problems can be addressed using perturbation analysis. In this paper, we propose a perturbation bound for the smallest singular value of a given matrix after appending a column, under the assumption that its initial coherence is not large, and we use this bound to derive a fast algorithm for feature extraction.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset