Provable Tensor-Train Format Tensor Completion by Riemannian Optimization

08/27/2021
by   Jian-Feng Cai, et al.
0

The tensor train (TT) format enjoys appealing advantages in handling structural high-order tensors. The recent decade has witnessed the wide applications of TT-format tensors from diverse disciplines, among which tensor completion has drawn considerable attention. Numerous fast algorithms, including the Riemannian gradient descent (RGrad) algorithm, have been proposed for the TT-format tensor completion. However, the theoretical guarantees of these algorithms are largely missing or sub-optimal, partly due to the complicated and recursive algebraic operations in TT-format decomposition. Moreover, existing results established for the tensors of other formats, for example, Tucker and CP, are inapplicable because the algorithms treating TT-format tensors are substantially different and more involved. In this paper, we provide, to our best knowledge, the first theoretical guarantees of the convergence of RGrad algorithm for TT-format tensor completion, under a nearly optimal sample size condition. The RGrad algorithm converges linearly with a constant contraction rate that is free of tensor condition number without the necessity of re-conditioning. We also propose a novel approach, referred to as the sequential second-order moment method, to attain a warm initialization under a similar sample size requirement. As a byproduct, our result even significantly refines the prior investigation of RGrad algorithm for matrix completion. Numerical experiments confirm our theoretical discovery and showcase the computational speedup gained by the TT-format decomposition.

READ FULL TEXT
research
11/19/2021

Parallel algorithms for computing the tensor-train decomposition

The tensor-train (TT) decomposition expresses a tensor in a data-sparse ...
research
04/05/2018

High-dimension Tensor Completion via Gradient-based Optimization Under Tensor-train Format

In this paper, we propose a novel approach to recover the missing entrie...
research
10/08/2021

Tensor train completion: local recovery guarantees via Riemannian optimization

In this work we estimate the number of randomly selected elements of a t...
research
02/28/2023

Riemannian preconditioned algorithms for tensor completion via tensor ring decomposition

We propose Riemannian preconditioned algorithms for the tensor completio...
research
05/12/2016

Exponential Machines

Modeling interactions between features improves the performance of machi...
research
06/08/2022

Constructive TT-representation of the tensors given as index interaction functions with applications

This paper presents a method to build explicit tensor-train (TT) represe...
research
06/17/2022

Tensor-on-Tensor Regression: Riemannian Optimization, Over-parameterization, Statistical-computational Gap, and Their Interplay

We study the tensor-on-tensor regression, where the goal is to connect t...

Please sign up or login with your details

Forgot password? Click here to reset