/Improving Multi-step Prediction of Learned Time Series Models

Improving Multi-step Prediction of Learned Time Series Models

Arun Venkatraman, Martial Hebert and J. Andrew (Drew) Bagnell
Conference Paper, Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15), January, 2015

Download Publication (PDF)

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.


Most typical statistical and machine learning ap- proaches to time series modeling optimize a single- step prediction error. In multiple-step simulation, the learned model is iteratively applied, feeding through the previous output as its new input. Any such pre- dictor however, inevitably introduces errors, and these compounding errors change the input distribution for future prediction steps, breaking the train-test i.i.d as- sumption common in supervised learning. We present an approach that reuses training data to make a no-regret learner robust to errors made during multi-step predic- tion. Our insight is to formulate the problem as imita- tion learning; the training data serves as a “demonstra- tor” by providing corrections for the errors made dur- ing multi-step prediction. By this reduction of multi- step time series prediction to imitation learning, we es- tablish theoretically a strong performance guarantee on the relation between training error and the multi-step prediction error. We present experimental results of our method, DAD, and show significant improvement over the traditional approach in two notably different domains, dynamic system modeling and video texture prediction.

BibTeX Reference
author = {Arun Venkatraman and Martial Hebert and J. Andrew (Drew) Bagnell},
title = {Improving Multi-step Prediction of Learned Time Series Models},
booktitle = {Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15)},
year = {2015},
month = {January},