Scalable uncertainty quantification for deep operator networks using randomized priors

We present a simple and effective approach for posterior uncertainty quantification in deep operator networks (DeepONets); an emerging paradigm for supervised learning in function spaces. We adopt a frequentist approach based on randomized prior ensembles, and put forth an efficient vectorized imple...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computer methods in applied mechanics and engineering 2022-09, Vol.399 (C), p.115399, Article 115399
Hauptverfasser:	Yang, Yibo, Kissas, Georgios, Perdikaris, Paris
Format:	Artikel
Sprache:	eng
Schlagworte:	Climate models Datasets Engineering Function space Hardware Mathematics Mechanics Uncertainty
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!