Better Batch for Deep Probabilistic Time Series Forecasting

Zhihao Zheng, Seongjin Choi, Lijun Sun
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:91-99, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-zheng24a, title = { Better Batch for Deep Probabilistic Time Series Forecasting }, author = {Zheng, Zhihao and Choi, Seongjin and Sun, Lijun}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {91--99}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/zheng24a/zheng24a.pdf}, url = {https://proceedings.mlr.press/v238/zheng24a.html}, 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. } }
Endnote
%0 Conference Paper %T Better Batch for Deep Probabilistic Time Series Forecasting %A Zhihao Zheng %A Seongjin Choi %A Lijun Sun %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-zheng24a %I PMLR %P 91--99 %U https://proceedings.mlr.press/v238/zheng24a.html %V 238 %X 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.
APA
Zheng, Z., Choi, S. & Sun, L.. (2024). Better Batch for Deep Probabilistic Time Series Forecasting . Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:91-99 Available from https://proceedings.mlr.press/v238/zheng24a.html.

Related Material