Are Tensor Decomposition Solutions Unique? On the global convergence of HOSVD and ParaFac algorithms

02/26/2009
by   Dijun Luo, et al.
0

For tensor decompositions such as HOSVD and ParaFac, the objective functions are nonconvex. This implies, theoretically, there exists a large number of local optimas: starting from different starting point, the iteratively improved solution will converge to different local solutions. This non-uniqueness present a stability and reliability problem for image compression and retrieval. In this paper, we present the results of a comprehensive investigation of this problem. We found that although all tensor decomposition algorithms fail to reach a unique global solution on random data and severely scrambled data; surprisingly however, on all real life several data sets (even with substantial scramble and occlusions), HOSVD always produce the unique global solution in the parameter region suitable to practical applications, while ParaFac produce non-unique solutions. We provide an eigenvalue based rule for the assessing the solution uniqueness.

READ FULL TEXT

page 6

page 7

page 8

research
04/22/2021

Uniqueness and stability for the solution of a nonlinear least squares problem

In this paper, we focus on the nonlinear least squares: _𝐱∈ℍ^d |A𝐱|-𝐛 wh...
research
06/15/2023

Tensor BM-Decomposition for Compression and Analysis of Spatio-Temporal Third-order Data

Given tensors 𝒜, ℬ, 𝒞 of size m × 1 × n, m × p × 1, and 1× p × n, respec...
research
03/13/2023

Provable Convergence of Tensor Decomposition-Based Neural Network Training

Advanced tensor decomposition, such as tensor train (TT), has been widel...
research
05/28/2019

Conditions on Features for Temporal Difference-Like Methods to Converge

The convergence of many reinforcement learning (RL) algorithms with line...
research
12/02/2022

Some properties of the solution of the vertical tensor complementarity problem

In this paper, we mainly focus on the existence and uniqueness of the ve...
research
12/07/2022

On the Global Solution of Soft k-Means

This paper presents an algorithm to solve the Soft k-Means problem globa...
research
02/04/2021

Restoring Uniqueness in MicroVM Snapshots

Code initialization – the step of loading code, executing static code, f...

Please sign up or login with your details

Forgot password? Click here to reset