A self-supervised learning approach for denoising autoregressive models with additive noise: finite and infinite variance cases

TL;DR

This paper introduces a self-supervised learning method for denoising autoregressive models affected by additive noise, including impulsive heavy-tailed noise, without requiring full noise distribution knowledge, improving signal recovery and forecasting.

Contribution

The paper presents a novel self-supervised denoising approach for autoregressive models with both finite and infinite variance noise, applicable without complete noise distribution information.

Findings

Strong denoising performance on synthetic and semi-synthetic data

Effective recovery of Gaussian and alpha-stable signals

Improved forecasting from noise-corrupted data

Abstract

The autoregressive time series model is a popular second-order stationary process, modeling a wide range of real phenomena. However, in applications, autoregressive signals are often corrupted by additive noise. Further, the autoregressive process and the corruptive noise may be highly impulsive, stemming from an infinite-variance distribution. The model estimation techniques that account for additional noise tend to show reduced efficacy when there is very strong noise present in the data, especially when the noise is heavy-tailed. In this paper, we propose a novel self-supervised learning method to denoise the additive noise-corrupted autoregressive model. Our approach is motivated by recent work in computer vision and does not require full knowledge of the noise distribution. We use the proposed method to recover exemplary finite- and infinite-variance autoregressive signals, namely, Gaussian and alpha-stable distributed signals, respectively, from their noise-corrupted versions. The simulation study conducted on both synthetic and semi-synthetic data demonstrates strong denoising performance of our method compared to several baseline methods, particularly when the corruption is significant and impulsive in nature. Finally, we apply the presented methodology to forecast the pure autoregressive signal from the noise-corrupted data.