Universality Theorems for Generative Models
arXiv:1905.11520
Abstract
Despite the fact that generative models are extremely successful in practice, the theory underlying this phenomenon is only starting to catch up with practice. In this work we address the question of the universality of generative models: is it true that neural networks can approximate any data manifold arbitrarily well? We provide a positive answer to this question and show that under mild assumptions on the activation function one can always find a feedforward neural network that maps the latent space onto a set located within the specified Hausdorff distance from the desired data manifold. We also prove similar theorems for the case of multiclass generative models and cycle generative models, trained to map samples from one manifold to another and vice versa.
References in corpus (7)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- The Mechanics of n-Player Differentiable Games
- Geometry Score: A Method For Comparing Generative Adversarial Networks
- Disconnected Manifold Learning for Generative Adversarial Networks
- Understanding GANs: the LQG Setting
- Generalized Tensor Models for Recurrent Neural Networks