Rank penalized estimators for high-dimensional matrices

Olga Klopp (1, 2)

1 CREST - Centre de Recherche en Économie et Statistique
2 CEREMADE - CEntre de REcherches en MAthématiques de la DEcision

In this paper we consider the trace regression model. Assume that we observe a small set of entries or linear combinations of entries of an unknown matrix $A_0$ corrupted by noise. We propose a new rank penalized estimator of $A_0$. For this estimator we establish general oracle inequality for the prediction error both in probability and in expectation. We also prove upper bounds for the rank of our estimator. Then we apply our general results to the problem of matrix completion when our estimator has a particularly simple form: it is obtained by hard thresholding of the singular values of a matrix constructed from the observations.

Mots clés: matrix completion; low rank matrix estimation; recovery of the rank; statistical learning

Domaines: Statistiques [math.ST]; Théorie [stat.TH]

Olga Klopp. Rank penalized estimators for high-dimensional matrices. 2011. ⟨hal-00583884v1⟩