Hybrid CUR-type decomposition of tensors in the Tucker format

02/05/2020
by   Erna Begovic, et al.
0

The paper introduces a hybrid approach to the CUR-type decomposition of tensors in the Tucker format. The idea of the hybrid algorithm is to write a tensor X as a product of a core tensor S, a matrix C obtained by extracting mode-k fibers of X, and matrices U_j, j=1,...,k-1,k+1,...,d, chosen to minimize the approximation error. The approximation can easily be modified to preserve the fibers in more than one mode. The approximation error obtained this way is smaller than the one from the standard tensor CUR-type method. This difference increases as the tensor dimension increases. It also increases as the number of modes in which the original fibers are preserved decreases.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/14/2023

A tensor SVD-like decomposition based on the semi-tensor product of tensors

In this paper, we define a semi-tensor product for third-order tensors. ...
research
10/26/2021

Rademacher Random Projections with Tensor Networks

Random projection (RP) have recently emerged as popular techniques in th...
research
03/06/2021

An Effective Approach to Minimize Error in Midpoint Ellipse Drawing Algorithm

The present paper deals with the generalization of Midpoint Ellipse Draw...
research
05/01/2023

A note on generalized tensor CUR approximation for tensor pairs and tensor triplets based on the tubal product

In this note, we briefly present a generalized tensor CUR (GTCUR) approx...
research
01/26/2022

VLDB 2021: Designing a Hybrid Conference

In 2020, while main database conferences one by one had to adopt a virtu...
research
11/02/2021

Trace maximization algorithm for the approximate tensor diagonalization

In this paper we develop a Jacobi-type algorithm for the (approximate) d...
research
09/17/2023

Dynasor: A Dynamic Memory Layout for Accelerating Sparse MTTKRP for Tensor Decomposition on Multi-core CPU

Sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP) is the most...

Please sign up or login with your details

Forgot password? Click here to reset