Predictive Whittle networks for time series

Zhongjie Yu, Fabrizio Ventola, Nils Thoma, Devendra Singh Dhami, Martin Mundt, Kristian Kersting
Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, PMLR 180:2320-2330, 2022.

Abstract

Recent developments have shown that modeling in the spectral domain improves the accuracy in time series forecasting. However, state-of-the-art neural spectral forecasters do not generally yield trustworthy predictions. In particular, they lack the means to gauge predictive likelihoods and provide uncertainty estimates. We propose predictive Whittle networks to bridge this gap, which exploit both the advances of neural forecasting in the spectral domain and leverage tractable likelihoods of probabilistic circuits. For this purpose, we propose a novel Whittle forecasting loss that makes use of these predictive likelihoods to guide the training of the neural forecasting component. We demonstrate how predictive Whittle networks improve real-world forecasting accuracy, while also allowing a transformation back into the time domain, in order to provide the necessary feedback of when the model’s prediction may become erratic.

Cite this Paper

BibTeX
@InProceedings{pmlr-v180-yu22b, title = {Predictive Whittle networks for time series}, author = {Yu, Zhongjie and Ventola, Fabrizio and Thoma, Nils and Dhami, Devendra Singh and Mundt, Martin and Kersting, Kristian}, booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence}, pages = {2320--2330}, year = {2022}, editor = {Cussens, James and Zhang, Kun}, volume = {180}, series = {Proceedings of Machine Learning Research}, month = {01--05 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v180/yu22b/yu22b.pdf}, url = {https://proceedings.mlr.press/v180/yu22b.html}, abstract = {Recent developments have shown that modeling in the spectral domain improves the accuracy in time series forecasting. However, state-of-the-art neural spectral forecasters do not generally yield trustworthy predictions. In particular, they lack the means to gauge predictive likelihoods and provide uncertainty estimates. We propose predictive Whittle networks to bridge this gap, which exploit both the advances of neural forecasting in the spectral domain and leverage tractable likelihoods of probabilistic circuits. For this purpose, we propose a novel Whittle forecasting loss that makes use of these predictive likelihoods to guide the training of the neural forecasting component. We demonstrate how predictive Whittle networks improve real-world forecasting accuracy, while also allowing a transformation back into the time domain, in order to provide the necessary feedback of when the model’s prediction may become erratic.} }
Endnote
%0 Conference Paper %T Predictive Whittle networks for time series %A Zhongjie Yu %A Fabrizio Ventola %A Nils Thoma %A Devendra Singh Dhami %A Martin Mundt %A Kristian Kersting %B Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2022 %E James Cussens %E Kun Zhang %F pmlr-v180-yu22b %I PMLR %P 2320--2330 %U https://proceedings.mlr.press/v180/yu22b.html %V 180 %X Recent developments have shown that modeling in the spectral domain improves the accuracy in time series forecasting. However, state-of-the-art neural spectral forecasters do not generally yield trustworthy predictions. In particular, they lack the means to gauge predictive likelihoods and provide uncertainty estimates. We propose predictive Whittle networks to bridge this gap, which exploit both the advances of neural forecasting in the spectral domain and leverage tractable likelihoods of probabilistic circuits. For this purpose, we propose a novel Whittle forecasting loss that makes use of these predictive likelihoods to guide the training of the neural forecasting component. We demonstrate how predictive Whittle networks improve real-world forecasting accuracy, while also allowing a transformation back into the time domain, in order to provide the necessary feedback of when the model’s prediction may become erratic.
APA
Yu, Z., Ventola, F., Thoma, N., Dhami, D.S., Mundt, M. & Kersting, K.. (2022). Predictive Whittle networks for time series. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 180:2320-2330 Available from https://proceedings.mlr.press/v180/yu22b.html.

Related Material