Physics-Informed Generative Adversarial Networks for Differential Equations
We developed a novel GAN formulation for solving differential equations with physics-informed neural networks.
Background
Consider differential equations of the form
\[F\left(t, \hat{\Psi}(t), \Delta \hat{\Psi}(t), \Delta^2 \hat{\Psi}(t), ...\right) = 0.\]To set up the problem for Differential Equation GAN (DEQGAN), we let
\[LHS = F\left(t, \hat{\Psi}(t), \Delta \hat{\Psi}(t), \Delta^2 \hat{\Psi}(t), ...\right),\]and \(RHS = 0.\)
Then we optimize the discriminator ($D$) and generator ($G$) with the gradients:
\[\eta_G = \nabla_{\theta_{g}} \frac{1}{m} \sum_{i=1}^{m} \log{ \left(1 - D \left( LHS^{(i)} \right) \right)},\] \[\eta_{D} = \nabla_{\theta_{d}} \frac{1}{m} \sum_{i=1}^{m} \left[ \log D \left( RHS^{(i)} \right) + \log \left( 1 - D \left( LHS^{(i)} \right) \right) \right],\]alternating between gradient ascent and descent steps for $D$ and $G$, respectively.
Visual representation of DEQGAN formulation.
Results
We obtain orders of magnitude lower error when compared to classic unsupervised neural-network approaches that use traditional loss functions (L1, L2, and Huber).
Comparison of DEQGAN to traditional physics-informed NNs on various problems.
Further Reading
- My master’s thesis
- Preprint paper
- ICML AI4Science paper
This post is licensed under CC BY 4.0 by the author.