Some theoretical properties of GANs
The Generative Adversarial Networks, GANs, are generative algorithms implemented by a system of two neural networks competing to each other in a zero-sum game framework. GANs have been introduced by \textit{I. Goodfellow} et al., [``Generative adversarial nets, Adv. Neural Inf. Proc. Sys. 27, 2672--2680 (2014)]. The aim of the present paper is to present a theoretical investigation of the original GANs algorithm. In the second section some optimality properties of the generative process in terms of Jensen-Shannon divergence are analyzed. The third section is devoted to approximation properties and one shows that the Jensen-Shannon divergence is a suitable criterion. Statistical properties are extensively discussed in the fourth section. Large sample properties of the parameter describing the empirically selected generator are studied. Conclusions and further research are presented in the fifth section and the proofs of results are contained in the section six.
- Some theoretical insights into Wasserstein GANs
- Deconstructing Generative Adversarial Networks
- Understanding Estimation and Generalization Error of Generative Adversarial Networks
- scientific article; zbMATH DE number 7267187
- Wasserstein proximal of GANs
- Generative modeling of convolutional neural networks
- Generalization error of GAN from the discriminator's perspective
- scientific article; zbMATH DE number 7626743
- Multi-projection of unequal dimension optimal transport theory for generative adversary networks
- Discriminator feature-based inference by recycling the discriminator of GANs
- A comprehensive survey and analysis of generative models in machine learning
- Generalization error of GAN from the discriminator's perspective
- Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
- Posterior asymptotics in Wasserstein metrics on the real line
- Generative adversarial networks with joint distribution moment matching
- A convenient infinite dimensional framework for generative adversarial learning
- Adversarial perturbations of deep neural networks
- A survey of image synthesis and editing with generative adversarial networks
- Some theoretical insights into Wasserstein GANs
- Least kth-order and Rényi generative adversarial networks
- scientific article; zbMATH DE number 7267187 (Why is no real title available?)
- Enforcing imprecise constraints on generative adversarial networks for emulating physical systems
- Training GANs with centripetal acceleration
- GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models
- Monte Carlo simulation of SDEs using GANs
- Geometrical Insights for Implicit Generative Modeling
- Minimax rate of distribution estimation on unknown submanifolds under adversarial losses
- Stochastic differential equation approximations of generative adversarial network training and its long-run behavior
- Optimal 1-Wasserstein distance for WGANs
- Statistical inference for generative adversarial networks and other minimax problems
- Minimax asymptotics
- On the statistical properties of generative adversarial models for low intrinsic data dimension
- Stock market simulator using hidden Markov generative model and its application in risk measurement
- Statistical guarantees for generative models without domination
- Statistical Quantile Learning for Large Additive Latent Variable Models
- ExceedGAN: simulation above extreme thresholds using generative adversarial networks
- GANs for generating EFT models
This page was built for publication: Some theoretical properties of GANs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2196234)
