Statistically Optimal and Computationally Efficient Low Rank Tensor Completion from Noisy Entries

11/14/2017
by   Dong Xia, et al.
0

In this article, we develop methods for estimating a low rank tensor from noisy observations on a subset of its entries to achieve both statistical and computational efficiencies. There have been a lot of recent interests in this problem of noisy tensor completion. Much of the attention has been focused on the fundamental computational challenges often associated with problems involving higher order tensors, yet very little is known about their statistical performance. To fill in this void, in this article, we characterize the fundamental statistical limits of noisy tensor completion by establishing minimax optimal rates of convergence for estimating a kth order low rank tensor under the general ℓ_p (1< p< 2) norm which suggest significant room for improvement over the existing approaches. Furthermore, we propose a polynomial-time computable estimating procedure based upon power iteration and a second-order spectral initialization that achieves the optimal rates of convergence. Our method is fairly easy to implement and numerical experiments are presented to further demonstrate the practical merits of our estimator.

READ FULL TEXT

page 25

page 26

research
04/08/2023

Statistical and computational rates in high rank tensor estimation

Higher-order tensor datasets arise commonly in recommendation systems, n...
research
11/03/2016

Cross: Efficient Low-rank Tensor Completion

The completion of tensors, or high-order arrays, attracts significant at...
research
11/11/2019

Nonconvex Low-Rank Symmetric Tensor Completion from Noisy Data

We study a noisy symmetric tensor completion problem of broad practical ...
research
06/15/2020

Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality

We study the distribution and uncertainty of nonconvex optimization for ...
research
06/06/2023

Online Tensor Learning: Computational and Statistical Trade-offs, Adaptivity and Optimal Regret

We investigate a generalized framework for estimating latent low-rank te...
research
07/20/2021

On Estimating Rank-One Spiked Tensors in the Presence of Heavy Tailed Errors

In this paper, we study the estimation of a rank-one spiked tensor in th...
research
02/27/2018

Breaking the 1/√(n) Barrier: Faster Rates for Permutation-based Models in Polynomial Time

Many applications, including rank aggregation and crowd-labeling, can be...

Please sign up or login with your details

Forgot password? Click here to reset