Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

7-2023

Abstract

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historicalvalue models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep timeindex models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a metaoptimization framework to learn deep time-index models which overcome these limitations, yielding an efficient and accurate forecasting model. Extensive experiments on real world datasets in the long sequence time-series forecasting setting demonstrate that our approach achieves competitive results with state-of-the-art methods, and is highly efficient. Code is available at https: //github.com/salesforce/DeepTime.

Keywords

time-series, forecasting, deep learning, implicit neural representation, meta-learning, time-index, non-stationary

Discipline

Artificial Intelligence and Robotics | Operations Research, Systems Engineering and Industrial Engineering

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 40th International Conference on Machine Learning 2023, Honolulu, HI, July 23-29

First Page

1

Last Page

21

Publisher

PMLR

City or Country

Honolulu, Hawaii, USA

Download

Share

COinS