Better Batch for Deep Probabilistic Time Series Forecasting

TL;DR

This paper introduces a novel training method for deep probabilistic time series forecasting that models error autocorrelation within mini-batches, leading to improved accuracy and uncertainty quantification.

Contribution

It proposes explicitly learning a time-varying covariance matrix over mini-batches to capture error serial correlation, enhancing forecasting performance.

Findings

Improved predictive accuracy across multiple datasets.

Enhanced uncertainty quantification through learned covariance.

Effective for different neural forecasting models.

Abstract

Deep probabilistic time series forecasting has gained attention for its ability to provide nonlinear approximation and valuable uncertainty quantification for decision-making. However, existing models often oversimplify the problem by assuming a time-independent error process and overlooking serial correlation. To overcome this limitation, we propose an innovative training method that incorporates error autocorrelation to enhance probabilistic forecasting accuracy. Our method constructs a mini-batch as a collection of $D$ consecutive time series segments for model training. It explicitly learns a time-varying covariance matrix over each mini-batch, encoding error correlation among adjacent time steps. The learned covariance matrix can be used to improve prediction accuracy and enhance uncertainty quantification. We evaluate our method on two different neural forecasting models and multiple public datasets. Experimental results confirm the effectiveness of the proposed approach in improving the performance of both models across a range of datasets, resulting in notable improvements in predictive accuracy.