Large covariance matrix estimation via penalized log-det heuristics
share
This paper provides a comprehensive estimation framework for large covariance matrices via a log-det heuristics augmented by a nuclear norm plus l_1 norm penalty. approximate factor models with a sparse residual covariance. The underlying assumptions allow for non-pervasive latent eigenvalues and a prominent residual covariance pattern. We prove that the aforementioned log-det heuristics is locally convex with a Lipschitz-continuous gradient, so that a proximal gradient algorithm may be stated to numerically solve the problem while controlling the threshold parameters. The proposed optimization strategy recovers with high probability both the covariance matrix components and the latent rank and the residual sparsity pattern, and performs systematically not worse than the corresponding estimators employing Frobenius loss in place of the log-det heuristics. The error bounds for the ensuing low rank and sparse covariance matrix estimators are established, and the identifiability condition for the latent geometric manifolds is provided. The validity of outlined results is highlighted by means of an exhaustive simulation study and a real financial data example involving euro zone banks.
READ FULL TEXT