Encoding Invariances in Deep Generative Models

Abstract

Reliable training of generative adversarial networks (GANs) typically require massive datasets in order to model complicated distributions. However, in several applications, training samples obey invariances that are \textit{a priori} known; for example, in complex physics simulations, the training data obey universal laws encoded as well-defined mathematical equations. In this paper, we propose a new generative modeling approach, InvNet, that can efficiently model data spaces with known invariances. We devise an adversarial training algorithm to encode them into data distribution. We validate our framework in three experimental settings: generating images with fixed motifs; solving nonlinear partial differential equations (PDEs); and reconstructing two-phase microstructures with desired statistical properties. We complement our experiments with several theoretical results.

References in corpus (18)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Which Training Methods for GANs do actually Converge?
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Statistical reconstruction of three-dimensional porous media from two-dimensional images
• On Convergence and Stability of GANs
• The Numerics of GANs
• Amortised MAP Inference for Image Super-resolution
• A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• Deep Learning the Physics of Transport Phenomena
• On the Limitations of First-Order Approximation in GAN Dynamics
• Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks
• How does Lipschitz Regularization Influence GAN Training?

Cited by in corpus (3)

• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data
• Adversarial sampling of unknown and high-dimensional conditional distributions