Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems

We explore using neural operators, or neural network representations of nonlinear maps between function spaces, to accelerate infinite-dimensional Bayesian inverse problems (BIPs) with models governed by nonlinear parametric partial differential equations (PDEs). Neural operators have gained signifi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	arXiv.org 2022-10
Hauptverfasser:	Cao, Lianghao, O'Leary-Roseberry, Thomas, Jha, Prashant K, J Tinsley Oden, Ghattas, Omar
Format:	Artikel
Sprache:	eng
Schlagworte:	Approximation Bayesian analysis Computer Science - Learning Computer Science - Numerical Analysis Computing costs Error correction Error correction & detection Error reduction Function space Inverse problems Mathematical models Mathematics - Numerical Analysis Neural networks Operators (mathematics) Parameters Partial differential equations Representations Statistics - Computation Statistics - Machine Learning Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!