Low-rank tensor completion: a Riemannian manifold preconditioning approach

05/26/2016
by   Hiroyuki Kasai, et al.
0

We propose a novel Riemannian manifold preconditioning approach for the tensor completion problem with rank constraint. A novel Riemannian metric or inner product is proposed that exploits the least-squares structure of the cost function and takes into account the structured symmetry that exists in Tucker decomposition. The specific metric allows to use the versatile framework of Riemannian optimization on quotient manifolds to develop preconditioned nonlinear conjugate gradient and stochastic gradient descent algorithms for batch and online setups, respectively. Concrete matrix representations of various optimization-related ingredients are listed. Numerical comparisons suggest that our proposed algorithms robustly outperform state-of-the-art algorithms across different synthetic and real-world datasets.

READ FULL TEXT

page 8

page 21

page 22

page 26

page 28

research
01/26/2021

New Riemannian preconditioned algorithms for tensor completion via polyadic decomposition

We propose new Riemannian preconditioned algorithms for low-rank tensor ...
research
12/04/2017

A Dual Framework for Low-rank Tensor Completion

We propose a novel formulation of the low-rank tensor completion problem...
research
11/12/2016

Riemannian Tensor Completion with Side Information

By restricting the iterate on a nonlinear manifold, the recently propose...
research
07/31/2019

Improved Pose Graph Optimization for Planar Motions Using Riemannian Geometry on the Manifold of Dual Quaternions

We present a novel Riemannian approach for planar pose graph optimizatio...
research
01/05/2018

Tensor Train decomposition on TensorFlow (T3F)

Tensor Train decomposition is used across many branches of machine learn...
research
02/04/2019

Adaptive stochastic gradient algorithms on Riemannian manifolds

Adaptive stochastic gradient algorithms in the Euclidean space have attr...
research
08/02/2021

Tensor completion using geodesics on Segre manifolds

We propose a Riemannian conjugate gradient (CG) optimization method for ...

Please sign up or login with your details

Forgot password? Click here to reset