Adversarial sampling of unknown and high-dimensional conditional distributions

Abstract

Many engineering problems require the prediction of realization-to-realization variability or a refined description of modeled quantities. In that case, it is necessary to sample elements from unknown high-dimensional spaces with possibly millions of degrees of freedom. While there exist methods able to sample elements from probability density functions (PDF) with known shapes, several approximations need to be made when the distribution is unknown. In this paper the sampling method, as well as the inference of the underlying distribution, are both handled with a data-driven method known as generative adversarial networks (GAN), which trains two competing neural networks to produce a network that can effectively generate samples from the training set distribution. In practice, it is often necessary to draw samples from conditional distributions. When the conditional variables are continuous, only one (if any) data point corresponding to a particular value of a conditioning variable may be available, which is not sufficient to estimate the conditional distribution. This work handles this problem using an a priori estimation of the conditional moments of a PDF. Two approaches, stochastic estimation, and an external neural network are compared here for computing these moments; however, any preferred method can be used. The algorithm is demonstrated in the case of the deconvolution of a filtered turbulent flow field. It is shown that all the versions of the proposed algorithm effectively sample the target conditional distribution with minimal impact on the quality of the samples compared to state-of-the-art methods. Additionally, the procedure can be used as a metric for the diversity of samples generated by a conditional GAN (cGAN) conditioned with continuous variables.

arXiv comment26 pages, 12 figures, 4 tables

References in corpus (27)

• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Machine Learning for Fluid Mechanics
• Toward Multimodal Image-to-Image Translation
• Energy-based Generative Adversarial Network
• Super-resolution reconstruction of turbulent flows with machine learning
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Unrolled Generative Adversarial Networks
• Improved Precision and Recall Metric for Assessing Generative Models
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Assessing Generative Models via Precision and Recall
• Genealogical particle analysis of rare events
• AdaGAN: Boosting Generative Models
• Diversity-Sensitive Conditional Generative Adversarial Networks
• Deep Learning the Physics of Transport Phenomena
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• Deep learning for presumed probability density function models
• Is Generator Conditioning Causally Related to GAN Performance?
• Turbulence Enrichment using Physics-informed Generative Adversarial Networks
• Rare event computation in deterministic chaotic systems using genealogical particle analysis
• From Deep to Physics-Informed Learning of Turbulence: Diagnostics
• A posteriori analysis of low-pass spatial filters for approximate deconvolution large eddy simulations of homogeneous incompressible flows
• Physics-Informed Neural Network Super Resolution for Advection-Diffusion Models
• Encoding Invariances in Deep Generative Models
• Modelling turbulent premixed flames using convolutional neural networks: application to sub-grid scale variance and filtered reaction rate
• A self-similarity principle for the computation of rare event probability