Residual-Quantile Adjustment for Adaptive Training of Physics-informed Neural Network

09/09/2022
by   Jiayue Han, et al.
0

Adaptive training methods for physical-informed neural network (PINN) require dedicated constructions of the distribution of weights assigned at each training sample. To efficiently seek such an optimal weight distribution is not a simple task and most existing methods choose the adaptive weights based on approximating the full distribution or the maximum of residuals. In this paper, we show that the bottleneck in the adaptive choice of samples for training efficiency is the behavior of the tail distribution of the numerical residual. Thus, we propose the Residual-Quantile Adjustment (RQA) method for a better weight choice for each training sample. After initially setting the weights proportional to the p-th power of the residual, our RQA method reassign all weights above q-quantile (90% for example) to the median value, so that the weight follows a quantile-adjusted distribution derived from the residuals. With the iterative reweighting technique, RQA is also very easy to implement. Experiment results show that the proposed method can outperform several adaptive methods on various partial differential equation (PDE) problems.

READ FULL TEXT
research
07/21/2022

A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

Physics-informed neural networks (PINNs) have shown to be an effective t...
research
03/15/2022

Physics-Informed Neural Networks with Adaptive Localized Artificial Viscosity

Physics-informed Neural Network (PINN) is a promising tool that has been...
research
05/05/2022

Investigating molecular transport in the human brain from MRI with physics-informed neural networks

In recent years, a plethora of methods combining deep neural networks an...
research
08/18/2022

Physics-Informed Neural Network Method for Parabolic Differential Equations with Sharply Perturbed Initial Conditions

In this paper, we develop a physics-informed neural network (PINN) model...
research
12/29/2021

PINNs for the Solution of the Hyperbolic Buckley-Leverett Problem with a Non-convex Flux Function

The displacement of two immiscible fluids is a common problem in fluid f...
research
05/04/2012

Weighted Patterns as a Tool for Improving the Hopfield Model

We generalize the standard Hopfield model to the case when a weight is a...

Please sign up or login with your details

Forgot password? Click here to reset