Generative Adversarial Neural Operators

by   Md Ashiqur Rahman, et al.

We propose the generative adversarial neural operator (GANO), a generative model paradigm for learning probabilities on infinite-dimensional function spaces. The natural sciences and engineering are known to have many types of data that are sampled from infinite-dimensional function spaces, where classical finite-dimensional deep generative adversarial networks (GANs) may not be directly applicable. GANO generalizes the GAN framework and allows for the sampling of functions by learning push-forward operator maps in infinite-dimensional spaces. GANO consists of two main components, a generator neural operator and a discriminator neural functional. The inputs to the generator are samples of functions from a user-specified probability measure, e.g., Gaussian random field (GRF), and the generator outputs are synthetic data functions. The input to the discriminator is either a real or synthetic data function. In this work, we instantiate GANO using the Wasserstein criterion and show how the Wasserstein loss can be computed in infinite-dimensional spaces. We empirically study GANOs in controlled cases where both input and output functions are samples from GRFs and compare its performance to the finite-dimensional counterpart GAN. We empirically study the efficacy of GANO on real-world function data of volcanic activities and show its superior performance over GAN. Furthermore, we find that for the function-based data considered, GANOs are more stable to train than GANs and require less hyperparameter optimization.


page 5

page 6

page 7

page 8

page 9

page 10


Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator

Generative Adversarial Networks (GANs) have shown great promise in model...

Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN

We relate the minimax game of generative adversarial networks (GANs) to ...

Neural SDEs as Infinite-Dimensional GANs

Stochastic differential equations (SDEs) are a staple of mathematical mo...

Functional Flow Matching

In this work, we propose Functional Flow Matching (FFM), a function-spac...

Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting

Generative adversarial networks (GANs) are an exciting alternative to al...

A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes

Quantifying biomechanical properties of the human vasculature could deep...

Please sign up or login with your details

Forgot password? Click here to reset