ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.10632
102
0

Hessian Geometry of Latent Space in Generative Models

12 June 2025
Alexander Lobashev
Dmitry Guskov
Maria Larchenko
M. Tamm
    DiffM
ArXiv (abs)PDFHTML
Main:9 Pages
13 Figures
Bibliography:2 Pages
2 Tables
Appendix:15 Pages
Abstract

This paper presents a novel method for analyzing the latent space geometry of generative models, including statistical physics models and diffusion models, by reconstructing the Fisher information metric. The method approximates the posterior distribution of latent variables given generated samples and uses this to learn the log-partition function, which defines the Fisher metric for exponential families. Theoretical convergence guarantees are provided, and the method is validated on the Ising and TASEP models, outperforming existing baselines in reconstructing thermodynamic quantities. Applied to diffusion models, the method reveals a fractal structure of phase transitions in the latent space, characterized by abrupt changes in the Fisher metric. We demonstrate that while geodesic interpolations are approximately linear within individual phases, this linearity breaks down at phase boundaries, where the diffusion model exhibits a divergent Lipschitz constant with respect to the latent space. These findings provide new insights into the complex structure of diffusion model latent spaces and their connection to phenomena like phase transitions. Our source code is available atthis https URL.

View on arXiv
@article{lobashev2025_2506.10632,
  title={ Hessian Geometry of Latent Space in Generative Models },
  author={ Alexander Lobashev and Dmitry Guskov and Maria Larchenko and Mikhail Tamm },
  journal={arXiv preprint arXiv:2506.10632},
  year={ 2025 }
}
Comments on this paper