Universality Theorems for Generative Models

05/27/2019
by   Valentin Khrulkov, et al.
4

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/07/2019

On Need for Topology Awareness of Generative Models

Manifold assumption in learning states that: the data lie approximately ...
research
07/14/2022

Comparing the latent space of generative models

Different encodings of datapoints in the latent space of latent-vector g...
research
04/30/2020

Robustness Certification of Generative Models

Generative neural networks can be used to specify continuous transformat...
research
10/14/2022

Commutativity and Disentanglement from the Manifold Perspective

In this paper, we interpret disentanglement from the manifold perspectiv...
research
12/18/2020

Flow-based Generative Models for Learning Manifold to Manifold Mappings

Many measurements or observations in computer vision and machine learnin...
research
06/02/2022

Score-Based Generative Models Detect Manifolds

Score-based generative models (SGMs) need to approximate the scores ∇log...
research
02/02/2022

GANSlider: How Users Control Generative Models for Images using Multiple Sliders with and without Feedforward Information

We investigate how multiple sliders with and without feedforward visuali...

Please sign up or login with your details

Forgot password? Click here to reset