An algorithm for arbitrary-order cumulant tensor calculation in a sliding window of data streams
From MaRDI portal
Publication:2314540
Abstract: High order cumulant tensors carry information about statistics of non-normally distributed multivariate data. In this work we present a new efficient algorithm for calculation of cumulants of arbitrary order in a sliding window for data streams. We showed that this algorithms enables speedups of cumulants updates compared to current algorithms. This algorithm can be used for processing on-line high-frequency multivariate data and can find applications in, e.g., on-line signal filtering and classification of data streams. To present an application of this algorithm, we propose an estimator of non-Gaussianity of a data stream based on the norms of high-order cumulant tensors. We show how to detect the transition from Gaussian distributed data to non-Gaussian ones in a~data stream. In order to achieve high implementation efficiency of operations on super-symmetric tensors, such as cumulant tensors, we employ the block structure to store and calculate only one hyper-pyramid part of such tensors.
Recommendations
- Efficient Computation of Higher-Order Cumulant Tensors
- Low-rank Tucker approximation of a tensor from streaming data
- Streaming Tensor Train Approximation
- Tensor-CUR Decompositions for Tensor-Based Data
- Tensor Approximation for Multidimensional and Multivariate Data
- An optimal statistical and computational framework for generalized tensor estimation
- Parallel tensor sampling in the hierarchical Tucker format
- A kernel-based framework to tensorial data analysis
- Scaling Probabilistic Tensor Canonical Polyadic Decomposition to Massive Data
- Approximation of Spatio-Temporal Random Processes Using Tensor Decomposition
Cites work
- Consumption-based asset pricing with higher cumulants
- CuBICA: Independent Component Analysis by Simultaneous Third- and Fourth-Order Cumulant Diagonalization
- Cummulants.jl
- Efficient Computation of Higher-Order Cumulant Tensors
- Eigenvalues of a real supersymmetric tensor
- Exploiting symmetry in tensors for high performance: multiplication with symmetric tensors
- Exploring complex and big data
- High-Resolution Direction Finding From Higher Order Statistics: The$2rm q$-MUSIC Algorithm
- scientific article; zbMATH DE number 3163305 (Why is no real title available?)
- scientific article; zbMATH DE number 5080942 (Why is no real title available?)
- scientific article; zbMATH DE number 4100386 (Why is no real title available?)
- scientific article; zbMATH DE number 194009 (Why is no real title available?)
- scientific article; zbMATH DE number 3443655 (Why is no real title available?)
- scientific article; zbMATH DE number 3319139 (Why is no real title available?)
- scientific article; zbMATH DE number 3105200 (Why is no real title available?)
- Julia: a fresh approach to numerical computing
- Knowledge discovery from data streams.
- Monte Carlo approximate tensor moment simulations.
- The art of computer programming. Volume 4A. Combinatorial algorithms. Part 1.
- The use of the multi-cumulant tensor analysis for the algorithmic optimisation of investment portfolios
Cited in
(3)
This page was built for publication: An algorithm for arbitrary-order cumulant tensor calculation in a sliding window of data streams
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2314540)
