I was reading this article https://www.di.ens.fr/~aspremon/PDF/CovSelSIMAX.pdf, whose goal is to estimate the covariance matrix from a the sample covariance matrix drawn from a distribution $X$.

' Given a sample covariance matrix, we solve a maximum likelihood problem penalized by the number of nonzero coefficients in the inverse covariance matrix. Our objective is to find a sparse representation of the sample data and to highlight conditional independence relationships between the sample variables.'

  1. The likelihood problem is only for the case where $X$ is a multivariate normal variable, so why did the author apply their method to a random distribution in section 4. ?

  2. Why are we seeking for a sparse covriance matrix ? Doesn't the covariance matrix have to be unique?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.