Variational Bayes Deep Operator Network: A data-driven Bayesian solver for parametric differential equations

by   Shailesh Garg, et al.

Neural network based data-driven operator learning schemes have shown tremendous potential in computational mechanics. DeepONet is one such neural network architecture which has gained widespread appreciation owing to its excellent prediction capabilities. Having said that, being set in a deterministic framework exposes DeepONet architecture to the risk of overfitting, poor generalization and in its unaltered form, it is incapable of quantifying the uncertainties associated with its predictions. We propose in this paper, a Variational Bayes DeepONet (VB-DeepONet) for operator learning, which can alleviate these limitations of DeepONet architecture to a great extent and give user additional information regarding the associated uncertainty at the prediction stage. The key idea behind neural networks set in Bayesian framework is that, the weights and bias of the neural network are treated as probability distributions instead of point estimates and, Bayesian inference is used to update their prior distribution. Now, to manage the computational cost associated with approximating the posterior distribution, the proposed VB-DeepONet uses variational inference. Unlike Markov Chain Monte Carlo schemes, variational inference has the capacity to take into account high dimensional posterior distributions while keeping the associated computational cost low. Different examples covering mechanics problems like diffusion reaction, gravity pendulum, advection diffusion have been shown to illustrate the performance of the proposed VB-DeepONet and comparisons have also been drawn against DeepONet set in deterministic framework.


page 14

page 16


Variational inference for large-scale models of discrete choice

Discrete choice models are commonly used by applied statisticians in num...

Learning to solve Bayesian inverse problems: An amortized variational inference approach

Inverse problems, i.e., estimating parameters of physical models from ex...

What Are Bayesian Neural Network Posteriors Really Like?

The posterior over Bayesian neural network (BNN) parameters is extremely...

Statistical Foundation of Variational Bayes Neural Networks

Despite the popularism of Bayesian neural networks in recent years, its ...

Rate Optimal Variational Bayesian Inference for Sparse DNN

Sparse deep neural network (DNN) has drawn much attention in recent stud...

Variational Bayes Neural Network: Posterior Consistency, Classification Accuracy and Computational Challenges

Bayesian neural network models (BNN) have re-surged in recent years due ...

Differentiable Bayesian Neural Network Inference for Data Streams

While deep neural networks (NNs) do not provide the confidence of its pr...

Please sign up or login with your details

Forgot password? Click here to reset