Recovery of Future Data via Convolution Nuclear Norm Minimization

09/06/2019
by   Guangcan Liu, et al.
0

This paper is about recovering the unseen future data from a given sequence of historical samples, so called as future data recovery—a significant problem closely related to time series forecasting. To address the problem, it is now prevalent to use deep neural networks, which are actually built upon the hypothesis that the desired evolution law can be learnt by using many observed samples to feed an overparameterized network. In practice, however, it is not always feasible to obtain a huge mass of training samples. To overcome the issue, we would suggest to consider a different methodology. Namely, we convert future data recovery into a more inclusive problem called sequential tensor completion (STC), which is to restore a latent tensor of sequential structure from a sampling of its entries. Unlike the ordinary tensor completion problem studied in the majority of literature, STC has a distinctive setup that allows the locations of missing entries to be distributed arbitrarily, integrating seamlessly the future values of time series into the framework of missing data. Then we propose two methods to address STC, including Discrete Fourier Transform based ℓ_1 minimization (DFT_ℓ_1) and Convolution Nuclear Norm Minimization (CNNM). We provide theoretical results to guarantee the recovery performance of the proposed methods. Remarkably, our theories disclose an important message; that is, under certain conditions, the unseen future values are indeed recoverable from the historical observations. Experiments on univariate time series, images and videos show encouraging results.

READ FULL TEXT
research
03/14/2022

Noisy Tensor Completion via Low-rank Tensor Ring

Tensor completion is a fundamental tool for incomplete data analysis, wh...
research
10/18/2021

A DCT-based Tensor Completion Approach for Recovering Color Images and Videos from Highly Undersampled Data

Recovering color images and videos from highly undersampled data is a fu...
research
07/07/2014

Novel methods for multilinear data completion and de-noising based on tensor-SVD

In this paper we propose novel methods for completion (from limited samp...
research
09/16/2019

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...
research
06/07/2018

Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements

The recent proposed Tensor Nuclear Norm (TNN) [Lu et al., 2016; 2018a] i...
research
07/05/2019

On Inferences from Completed Data

Matrix completion has become an extremely important technique as data sc...
research
04/23/2021

Time Series Forecasting via Learning Convolutionally Low-Rank Models

Recently, <cit.> studied the rather challenging problem of time series f...

Please sign up or login with your details

Forgot password? Click here to reset