Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent

05/23/2016

∙

by   Qinqing Zheng, et al.

∙

0

∙

share

We address the rectangular matrix completion problem by lifting the unknown matrix to a positive semidefinite matrix in higher dimension, and optimizing a nonconvex objective over the semidefinite factor using a simple gradient descent scheme. With O( μ r^2 κ^2 n (μ, n)) random observations of a n_1 × n_2 μ-incoherent matrix of rank r and condition number κ, where n = (n_1, n_2), the algorithm linearly converges to the global optimum with high probability.