LGMay 11, 2022

Efficient Automated Deep Learning for Time Series Forecasting

arXiv:2205.05511v320 citationsh-index: 85
AI Analysis

This work addresses the problem of automating deep learning for time series forecasting, which is incremental as it adapts existing AutoDL methods to a new domain.

The paper tackles the lack of general Automated Deep Learning frameworks for time series forecasting by proposing an efficient joint optimization approach for neural architecture and hyperparameters, resulting in a system that significantly outperforms established baselines across several datasets.

Recent years have witnessed tremendously improved efficiency of Automated Machine Learning (AutoML), especially Automated Deep Learning (AutoDL) systems, but recent work focuses on tabular, image, or NLP tasks. So far, little attention has been paid to general AutoDL frameworks for time series forecasting, despite the enormous success in applying different novel architectures to such tasks. In this paper, we propose an efficient approach for the joint optimization of neural architecture and hyperparameters of the entire data processing pipeline for time series forecasting. In contrast to common NAS search spaces, we designed a novel neural architecture search space covering various state-of-the-art architectures, allowing for an efficient macro-search over different DL approaches. To efficiently search in such a large configuration space, we use Bayesian optimization with multi-fidelity optimization. We empirically study several different budget types enabling efficient multi-fidelity optimization on different forecasting datasets. Furthermore, we compared our resulting system, dubbed \system, against several established baselines and show that it significantly outperforms all of them across several datasets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes