Adaptive Physics-Informed Neural Networks for Markov-Chain Monte Carlo
arXiv:2008.01604
Abstract
In this paper, we propose the Adaptive Physics-Informed Neural Networks (APINNs) for accurate and efficient simulation-free Bayesian parameter estimation via Markov-Chain Monte Carlo (MCMC). We specifically focus on a class of parameter estimation problems for which computing the likelihood function requires solving a PDE. The proposed method consists of: (1) constructing an offline PINN-UQ model as an approximation to the forward model; and (2) refining this approximate model on the fly using samples generated from the MCMC sampler. The proposed APINN method constantly refines this approximate model on the fly and guarantees that the approximation error is always less than a user-defined residual error threshold. We numerically demonstrate the performance of the proposed APINN method in solving a parameter estimation problem for a system governed by the Poisson equation.
arXiv commentarXiv admin note: text overlap with arXiv:1806.02957
References in corpus (11)
- ADADELTA: An Adaptive Learning Rate Method
- An overview of gradient descent optimization algorithms
- MCMC using Hamiltonian dynamics
- Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
- Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- A unified deep artificial neural network approach to partial differential equations in complex geometries
- A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- A deep surrogate approach to efficient Bayesian inversion in PDE and integral equation models