B-DeepONet: an enhanced Bayesian deeponet for solving noisy parametric PDEs using accelerated replica exchange SGLD

DOI10.1016/J.JCP.2022.111713MaRDI QIDQ2106911zbMATH OpenOpenAlexFDO

Authors Guang Lin, Christian Moya, Zecheng Zhang

Publication date 29 November 2022

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jcp.2022.111713

zbMATH Keywords

Bayesian methodnoisy datareplica exchangeLangevin diffusiondeep operator networkparametric PDE

Mathematics Subject Classification ID

Parabolic equations and parabolic systems (35Kxx) Miscellaneous topics in partial differential equations (35Rxx) Probabilistic methods, stochastic differential equations (65Cxx)

Recommendations

• On the training and generalization of deep operator networks
• Predictions of transient vector solution fields with sequential deep operator network
• Semi-supervised invertible neural operators for Bayesian inverse problems
• RandONets: shallow networks with random projections for learning linear and nonlinear operators

Cites work

• A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
• A multi-stage deep learning based algorithm for multiscale model reduction
• Computational multiscale methods for quasi-gas dynamic equations
• DeepM\&Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• Diffusion for Global Optimization in $\mathbb{R}^n $
• Laplace's method revisited: Weak convergence of probability measures
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Solving parametric PDE problems with artificial neural networks

Cited in

(12)

• MODNO: multi-operator learning with distributed neural operators
• Multi-agent reinforcement learning aided sampling algorithms for a class of multiscale inverse problems
• On the influence of over-parameterization in manifold based surrogates and deep neural operators
• Reliable extrapolation of deep neural operators informed by physics or sparse observations
• RiemannONets: interpretable neural operators for Riemann problems
• RandONets: shallow networks with random projections for learning linear and nonlinear operators
• Predictions of transient vector solution fields with sequential deep operator network
• Bayesian deep operator learning for homogenized to fine-scale maps for multiscale PDE
• D2NO: efficient handling of heterogeneous input function spaces with distributed deep neural operators
• A discretization-invariant extension and analysis of some deep operator networks
• On the training and generalization of deep operator networks
• Conformalized-DeepONet: a distribution-free framework for uncertainty quantification in deep operator networks

Describes a project that uses

Uses Software

• DeepONet

This page was built for publication: B-DeepONet: an enhanced Bayesian deeponet for solving noisy parametric PDEs using accelerated replica exchange SGLD

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2106911)