Sharp Oracle Inequalities in Low Rank Estimation

Abstract

The paper deals with the problem of penalized empirical risk minimization over a convex set of linear functionals on the space of Hermitian matrices with convex loss and nuclear norm penalty. Such penalization is often used in low rank matrix recovery in the cases when the target function can be well approximated by a linear functional generated by a Hermitian matrix of relatively small rank (comparing with the size of the matrix). Our goal is to prove sharp low rank oracle inequalities that involve the excess risk (the approximation error) with constant equal to one and the random error term with correct dependence on the rank of the oracle.

References in corpus (2)

• Estimation of high-dimensional low-rank matrices
• Tight oracle bounds for low-rank matrix recovery from a minimal number of random measurements

Cited by in corpus (1)

• Nonparametric Estimation of Low Rank Matrix Valued Function