Nimishakavi, Madhav and Jawanpuria, Pratik and Mishra, Bamdev (2018) A dual framework for low-rank tensor completion. In: 32nd Conference on Neural Information Processing Systems (NIPS), 2 - 8 December , 2018, Montreal, Canada.
|
PDF
Adv_Neu_Inf_Pro_Sys_31_2018.pdf - Published Version Download (608kB) | Preview |
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.
Item Type: | Conference Proceedings |
---|---|
Series.: | Advances in Neural Information Processing Systems |
Publisher: | NEURAL INFORMATION PROCESSING SYSTEMS (NIPS) |
Additional Information: | Copyright belongs to NEURAL INFORMATION PROCESSING SYSTEMS (NIPS) |
Department/Centre: | Division of Electrical Sciences > Computer Science & Automation |
Date Deposited: | 21 Apr 2019 08:07 |
Last Modified: | 21 Apr 2019 08:07 |
URI: | http://eprints.iisc.ac.in/id/eprint/62309 |
Actions (login required)
![]() |
View Item |