Low-rank matrix completion by Riemannian optimization---extended version
This work addresses the matrix completion problem, offering a scalable algorithm that outperforms state-of-the-art methods for large-scale applications.
The paper proposes a new algorithm for low-rank matrix completion that minimizes least-square distance on sampled entries over the Riemannian manifold of fixed-rank matrices, using conjugate gradients. Numerical experiments show it scales well for large problems and outperforms most existing solvers.
The matrix completion problem consists of finding or approximating a low-rank matrix based on a few samples of this matrix. We propose a new algorithm for matrix completion that minimizes the least-square distance on the sampling set over the Riemannian manifold of fixed-rank matrices. The algorithm is an adaptation of classical non-linear conjugate gradients, developed within the framework of retraction-based optimization on manifolds. We describe all the necessary objects from differential geometry necessary to perform optimization over this low-rank matrix manifold, seen as a submanifold embedded in the space of matrices. In particular, we describe how metric projection can be used as retraction and how vector transport lets us obtain the conjugate search directions. Finally, we prove convergence of a regularized version of our algorithm under the assumption that the restricted isometry property holds for incoherent matrices throughout the iterations. The numerical experiments indicate that our approach scales very well for large-scale problems and compares favorably with the state-of-the-art, while outperforming most existing solvers.