Generalization Properties of Optimal Transport GANs with Latent Distribution Learning
arXiv:2007.14641
Abstract
The Generative Adversarial Networks (GAN) framework is a well-established paradigm for probability matching and realistic sample generation. While recent attention has been devoted to studying the theoretical properties of such models, a full theoretical understanding of the main building blocks is still missing. Focusing on generative models with Optimal Transport metrics as discriminators, in this work we study how the interplay between the latent distribution and the complexity of the pushforward map (generator) affects performance, from both statistical and modelling perspectives. Motivated by our analysis, we advocate learning the latent distribution as well as the pushforward map within the GAN paradigm. We prove that this can lead to significant advantages in terms of sample complexity.
arXiv comment34 pages, 6 figures
References in corpus (11)
- Auto-Encoding Variational Bayes
- Conditional Image Generation with PixelCNN Decoders
- Pixel Recurrent Neural Networks
- Generalization and Equilibrium in Generative Adversarial Nets (GANs)
- Sample Complexity of Sinkhorn divergences
- Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
- Density Estimation in Infinite Dimensional Exponential Families
- On the Convergence and Robustness of Training GANs with Regularized Optimal Transport
- Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images
- Approximability of Discriminators Implies Diversity in GANs
- Finding Mixed Nash Equilibria of Generative Adversarial Networks
Cited by in corpus (7)
- Some Theoretical Insights into Wasserstein GANs
- Statistical guarantees for generative models without domination
- Rates of convergence for density estimation with generative adversarial networks
- SDE approximations of GANs training and its long-run behavior
- Optimal 1-Wasserstein Distance for WGANs
- Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
- Understanding Entropic Regularization in GANs