1. Home
  2. Two-matrix latent decomposition

Two-matrix latent decomposition

is the solution of the eigenvalue decomposition

A X = W X L

The matrices A and W both have n rows, and matrix W must be positive semi-definite. The latent roots are the n elements of the diagonal matrix L and are the successive maxima of

l = (x′ A x) / (x′ W x)

where x is the corresponding column of the n-by-n matrix X, normalized so that

X′ W X = I.

Updated on December 4, 2017

Was this article helpful?