Skip to yearly menu bar Skip to main content


Poster

A Dual Framework for Low-rank Tensor Completion

Madhav Nimishakavi · Pratik Kumar Jawanpuria · Bamdev Mishra

Room 517 AB #146

Keywords: [ Nonlinear Dimensionality Reduction and Manifold Learning ] [ Matrix and Tensor Factorization ] [ Non-Convex Optimization ]


Abstract:

One of the popular approaches for low-rank tensor completion is to use the latent trace norm regularization. However, most existing works in this direction learn a sparse combination of tensors. In this work, we fill this gap by proposing a variant of the latent trace norm that helps in learning a non-sparse combination of tensors. We develop a dual framework for solving the low-rank tensor completion problem. We first show a novel characterization of the dual solution space with an interesting factorization of the optimal solution. Overall, the optimal solution is shown to lie on a Cartesian product of Riemannian manifolds. Furthermore, we exploit the versatile Riemannian optimization framework for proposing computationally efficient trust region algorithm. The experiments illustrate the efficacy of the proposed algorithm on several real-world datasets across applications.

Live content is unavailable. Log in and register to view live content