44
6

Optimal spectral norm rates for noisy low-rank matrix completion

Abstract

In this paper we consider the trace regression model where nn entries or linear combinations of entries of an unknown m1×m2m_1\times m_2 matrix A0A_0 corrupted by noise are observed. We establish for the nuclear-norm penalized estimator of A0A_0 introduced in \cite{KLT} a general sharp oracle inequality with the spectral norm for arbitrary values of n,m1,m2n,m_1,m_2 under an incoherence condition on the sampling distribution Π\Pi of the observed entries. Then, we apply this method to the matrix completion problem. In this case, we prove that it satisfies an optimal oracle inequality for the spectral norm, thus improving upon the only existing result \cite{KLT} concerning the spectral norm, which assumes that the sampling distribution is uniform. Note that our result is valid, in particular, in the high-dimensional setting m1m2nm_1m_2\gg n. Finally we show that the obtained rate is optimal up to logarithmic factors in a minimax sense.

View on arXiv
Comments on this paper