Conformalized-deeponet: A distribution-free framework for uncertainty quantification in deep operator networks

C Moya, A Mollaali, Z Zhang, L Lu, G Lin - Physica D: Nonlinear …, 2025 - Elsevier
In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification
(UQ) framework, to obtain prediction intervals with coverage guarantees for Deep Operator …

Using uncertainty quantification to characterize and improve out-of-domain learning for PDEs

SC Mouli, DC Maddix, S Alizadeh, G Gupta… - ar**s between function spaces, offer an efficient
alternative for solving partial differential equations. However, their generalization to out-of …

Uncertainty quantification for DeepONets with ensemble Kalman inversion

A Pensoneault, X Zhu - Journal of computational physics, 2025 - Elsevier
In recent years, operator learning, particularly the DeepONet, has received much attention
for efficiently learning complex map**s between input and output functions across diverse …

A physics-informed transformer neural operator for learning generalized solutions of initial boundary value problems

SK Boya, D Subramani - arxiv preprint arxiv:2412.09009, 2024 - arxiv.org
Initial boundary value problems arise commonly in applications with engineering and
natural systems governed by nonlinear partial differential equations (PDEs). Operator …

[HTML][HTML] Exploring the Trade-Off in the Variational Information Bottleneck for Regression with a Single Training Run

S Kudo, N Ono, S Kanaya, M Huang - Entropy, 2024 - pmc.ncbi.nlm.nih.gov
An information bottleneck (IB) enables the acquisition of useful representations from data by
retaining necessary information while reducing unnecessary information. In its objective …

Orthogonal greedy algorithm for linear operator learning with shallow neural network

Y Lin, J Jia, YJ Lee, R Zhang - arxiv preprint arxiv:2501.02791, 2025 - arxiv.org
Greedy algorithms, particularly the orthogonal greedy algorithm (OGA), have proven
effective in training shallow neural networks for fitting functions and solving partial …

A survey on machine learning approaches for uncertainty quantification of engineering systems

Y Shi, P Wei, K Feng, DC Feng, M Beer - Machine Learning for …, 2025 - Springer
Uncertainty quantification (UQ) is essential for understanding and mitigating the impact of
pervasive uncertainties in engineering systems, playing a crucial role in modern …