2022/05/11 by Difan Deng, Florian Karl, Deng, Difan +7 · 2 citations
Computer Science · Decision Sciences · #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Machine Learning and Data Classification #Stock Market Forecasting Methods
paper · pdf · doi:10.48550/arxiv.2205.05511
openalex publication_date 2022/05/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.