High order cumulant tensors and algorithm for their calculation

by   Krzysztof Domino, et al.
Institute of Theoretical and Applied Informatics

In this paper, we introduce a novel algorithm for calculating arbitrary order cumulants of multidimensional data. Since the m^th order cumulant can be presented in the form of an m-dimensional tensor, the algorithm is presented using tensor operations. The algorithm provided in the paper takes advantage of super-symmetry of cumulant and moment tensors. We show that the proposed algorithm considerably reduces the computational complexity and the computational memory requirement of cumulant calculation as compared with existing algorithms. For the sizes of interest, the reduction is of the order of m! compared to the naive algorithm.


page 1

page 2

page 3

page 4


Best Rank-One Tensor Approximation and Parallel Update Algorithm for CPD

A novel algorithm is proposed for CANDECOMP/PARAFAC tensor decomposition...

Adaptive Cross Tubal Tensor Approximation

In this paper, we propose a new adaptive cross algorithm for computing a...

On updates of high order cumulant tensors

High order cumulants carry information about statistics of non--normally...

RotEqNet: Rotation-Equivariant Network for Fluid Systems with Symmetric High-Order Tensors

In the recent application of scientific modeling, machine learning model...

Automating Personnel Rostering by Learning Constraints Using Tensors

Many problems in operations research require that constraints be specifi...

Low-complexity Multidimensional DCT Approximations

In this paper, we introduce low-complexity multidimensional discrete cos...

High Performance Rearrangement and Multiplication Routines for Sparse Tensor Arithmetic

Researchers are increasingly incorporating numeric high-order data, i.e....

Code Repositories


Calculates multivariate cumulants of any order

view repo

Please sign up or login with your details

Forgot password? Click here to reset