Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold

Anupam Chaudhuri, Anj Simmons, Mohamed Abdelrazek
3/8/2024
cs.LGcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

This paper presents our experiments to quantify the manifolds learned by ML models (in our experiment, we use a GAN model) as they train. We compare the manifolds learned at each epoch to the real manifolds representing the real data. To quantify a manifold, we study the intrinsic dimensions and topological features of the manifold learned by the ML model, how these metrics change as we continue to train the model, and whether these metrics convergence over the course of training to the metrics of the real data manifold.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections

85% match1 repo42024

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds

85% match2026

A Geometric Framework for Understanding Memorization in Generative Models

84% match2024

The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold

84% match1 repo192023

Hardness of Learning Neural Networks under the Manifold Hypothesis

84% match1 repo22024

Exploring the Manifold of Neural Networks Using Diffusion Geometry

83% match2024

Cite this paper

@article{chaudhuri2024quantifying,
  title  = {Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold},
  author = {Anupam Chaudhuri and Anj Simmons and Mohamed Abdelrazek},
  year   = {2024},
  eprint = {2403.05033},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.05033v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.05033.svg)](https://codeofpaper.com/paper/2403.05033)

Discussion