Transform-Based Multilinear Dynamical System for Tensor Time Series Analysis

by   Weijun Lu, et al.
Columbia University
Xidian University

We propose a novel multilinear dynamical system (MLDS) in a transform domain, named L-MLDS, to model tensor time series. With transformations applied to a tensor data, the latent multidimensional correlations among the frontal slices are built, and thus resulting in the computational independence in the transform domain. This allows the exact separability of the multi-dimensional problem into multiple smaller LDS problems. To estimate the system parameters, we utilize the expectation-maximization (EM) algorithm to determine the parameters of each LDS. Further, L-MLDSs significantly reduce the model parameters and allows parallel processing. Our general L-MLDS model is implemented based on different transforms: discrete Fourier transform, discrete cosine transform and discrete wavelet transform. Due to the nonlinearity of these transformations, L-MLDS is able to capture the nonlinear correlations within the data unlike the MLDS rogers2013multilinear which assumes multi-way linear correlations. Using four real datasets, the proposed L-MLDS is shown to achieve much higher prediction accuracy than the state-of-the-art MLDS and LDS with an equal number of parameters under different noise models. In particular, the relative errors are reduced by 50%∼ 99%. Simultaneously, L-MLDS achieves an exponential improvement in the model's training time than MLDS.


page 1

page 2

page 3

page 4


Discrete cosine transform LSQR and GMRES methods for multidimensional ill-posed problems

In the present work, we propose new tensor Krylov subspace method for il...

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Multivariate time-series forecasting plays a crucial role in many real-w...

New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms

Some conventional transforms such as Discrete Walsh-Hadamard Transform (...

Framelet Representation of Tensor Nuclear Norm for Third-Order Tensor Completion

The main aim of this paper is to develop a framelet representation of th...

Forecasting Multilinear Data via Transform-Based Tensor Autoregression

In the era of big data, there is an increasing demand for new methods fo...

Sig-Splines: universal approximation and convex calibration of time series generative models

We propose a novel generative model for multivariate discrete-time time ...

Predicting Multidimensional Data via Tensor Learning

The analysis of multidimensional data is becoming a more and more releva...

Please sign up or login with your details

Forgot password? Click here to reset