ReCycle: Fast and Efficient Long Time Series Forecasting with Residual Cyclic Transformers

Transformers have recently gained prominence in long time series forecasting by elevating accuracies in a variety of use cases. Regrettably, in the race for better predictive performance the overhead of model architectures has grown onerous, leading to models with computational demand infeasible for...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-05
Hauptverfasser:	Weyrauch, Arvid, Steens, Thomas, Taubert, Oskar, Hanke, Benedikt, Aslan Eqbal, Götz, Ewa, Streit, Achim, Götz, Markus, Debus, Charlotte
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Complexity Edge computing Energy consumption Forecasting Mathematical models Performance prediction Run time (computers) Smoothing Time series Transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!