Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems

Abstract

We present a probabilistic deep learning methodology that enables the construction of predictive data-driven surrogates for stochastic systems. Leveraging recent advances in variational inference with implicit distributions, we put forth a statistical inference framework that enables the end-to-end training of surrogate models on paired input-output observations that may be stochastic in nature, originate from different information sources of variable fidelity, or be corrupted by complex noise processes. The resulting surrogates can accommodate high-dimensional inputs and outputs and are able to return predictions with quantified uncertainty. The effectiveness our approach is demonstrated through a series of canonical studies, including the regression of noisy data, multi-fidelity modeling of stochastic processes, and uncertainty propagation in high-dimensional dynamical systems.

37 pages, 11 figures, Submitted to Computational Mechanics

References in corpus (5)

• From optimal transport to generative modeling: the VEGAN cookbook
• GAN and VAE from an Optimal Transport Point of View
• Symmetric Variational Autoencoder and Connections to Adversarial Learning
• Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
• A deep generative model for single-cell RNA sequencing with application to detecting differentially expressed genes