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

06/15/2020
by   Changxiao Cai, et al.
7

We study the distribution and uncertainty of nonconvex optimization for noisy tensor completion – the problem of estimating a low-rank tensor given incomplete and corrupted observations of its entries. Focusing on a two-stage estimation algorithm proposed by Cai et al. (2019), we characterize the distribution of this nonconvex estimator down to fine scales. This distributional theory in turn allows one to construct valid and short confidence intervals for both the unseen tensor entries and the unknown tensor factors. The proposed inferential procedure enjoys several important features: (1) it is fully adaptive to noise heteroscedasticity, and (2) it is data-driven and automatically adapts to unknown noise distributions. Furthermore, our findings unveil the statistical optimality of nonconvex tensor completion: it attains un-improvable ℓ_2 accuracy – including both the rates and the pre-constants – when estimating both the unknown tensor and the underlying tensor factors.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/10/2019

Inference and Uncertainty Quantification for Noisy Matrix Completion

Noisy matrix completion aims at estimating a low-rank matrix given only ...
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
11/14/2017

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

In this article, we develop methods for estimating a low rank tensor fro...
research
01/14/2020

Inference for linear forms of eigenvectors under minimal eigenvalue separation: Asymmetry and heteroscedasticity

A fundamental task that spans numerous applications is inference and unc...
research
07/23/2018

Scalable Tensor Completion with Nonconvex Regularization

Low-rank tensor completion problem aims to recover a tensor from limited...
research
01/26/2015

Noisy Tensor Completion via the Sum-of-Squares Hierarchy

In the noisy tensor completion problem we observe m entries (whose locat...
research
07/26/2021

Inference for Heteroskedastic PCA with Missing Data

This paper studies how to construct confidence regions for principal com...

Please sign up or login with your details

Forgot password? Click here to reset