Power Iteration for Tensor PCA

12/26/2020
by   Jiaoyang Huang, et al.
0

In this paper, we study the power iteration algorithm for the spiked tensor model, as introduced in [44]. We give necessary and sufficient conditions for the convergence of the power iteration algorithm. When the power iteration algorithm converges, for the rank one spiked tensor model, we show the estimators for the spike strength and linear functionals of the signal are asymptotically Gaussian; for the multi-rank spiked tensor model, we show the estimators are asymptotically mixtures of Gaussian. This new phenomenon is different from the spiked matrix model. Using these asymptotic results of our estimators, we construct valid and efficient confidence intervals for spike strengths and linear functionals of the signals.

READ FULL TEXT

page 12

page 15

research
11/16/2022

On the Accuracy of Hotelling-Type Tensor Deflation: A Random Tensor Analysis

Leveraging on recent advances in random tensor theory, we consider in th...
research
11/04/2014

A statistical model for tensor PCA

We consider the Principal Component Analysis problem for large tensors o...
research
11/07/2022

Lower Bounds for the Convergence of Tensor Power Iteration on Random Overcomplete Models

Tensor decomposition serves as a powerful primitive in statistics and ma...
research
03/02/2023

Noda Iteration for Computing Generalized Tensor Eigenpairs

In this paper, we propose the tensor Noda iteration (NI) and its inexact...
research
12/23/2021

Selective Multiple Power Iteration: from Tensor PCA to gradient-based exploration of landscapes

We propose Selective Multiple Power Iterations (SMPI), a new algorithm t...
research
08/04/2023

Distributional Theory and Statistical Inference for Linear Functions of Eigenvectors with Small Eigengaps

Spectral methods have myriad applications in high-dimensional statistics...
research
08/31/2019

Statistical Inferences of Linear Forms for Noisy Matrix Completion

We introduce a flexible framework for making inferences about general li...

Please sign up or login with your details

Forgot password? Click here to reset