Hessian Geometry of Latent Space in Generative Models

• URL: http://arxiv.org/abs/2506.10632v1
• Date: Thu, 12 Jun 2025 12:17:40 GMT
• Title: Hessian Geometry of Latent Space in Generative Models
• Authors: Alexander Lobashev, Dmitry Guskov, Maria Larchenko, Mikhail Tamm,
• Abstract summary: We present a novel method for analyzing the latent space geometry of generative models.<n>The method approximates the posterior distribution of latent variables given generated samples.<n>It is validated on the Ising and TASEP models, outperforming existing baselines in reconstructing thermodynamic quantities.
• Score: 41.94295877935867
• License: http://creativecommons.org/licenses/by/4.0/
• 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 at https://github.com/alobashev/hessian-geometry-of-diffusion-models.

Related papers

• Continuous Diffusion Model for Language Modeling [57.396578974401734]
  Existing continuous diffusion models for discrete data have limited performance compared to discrete approaches.<n>We propose a continuous diffusion model for language modeling that incorporates the geometry of the underlying categorical distribution.
  arXiv  Detail & Related papers  (2025-02-17T08:54:29Z)
• Analysis of Diffusion Models for Manifold Data [8.539326630369592]
  We analyze the time reversed dynamics of generative diffusion models.<n>An important tool used in our analysis is the exact formula for the mutual information (or free energy) of Generalized Linear Models.
  arXiv  Detail & Related papers  (2025-02-01T08:14:35Z)
• A solvable generative model with a linear, one-step denoiser [0.0]
  We develop an analytically tractable single-step diffusion model based on a linear denoiser and present an explicit formula for the Kullback-Leibler divergence.<n>For large-scale practical diffusion models, we explain why a higher number of diffusion steps enhances production quality.
  arXiv  Detail & Related papers  (2024-11-26T19:00:01Z)
• What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models [17.273596999339077]
  We study the local geometry of the learned manifold and its relationship to generation outcomes for a wide range of generative models.<n>We provide quantitative and qualitative evidence showing that for a given latent-image pair, the local descriptors are indicative of generation aesthetics, diversity, and memorization by the generative model.
  arXiv  Detail & Related papers  (2024-08-15T17:59:06Z)
• Generative prediction of flow fields around an obstacle using the diffusion model [12.094115138998745]
  We propose a geometry-to-flow diffusion model that utilizes obstacle shape as input to predict a flow field around an obstacle.<n>A Markov process is conditioned on the obstacle geometry, estimating the noise to be removed at each step.<n>We train the geometry-to-flow diffusion model using a dataset of flows around simple obstacles, including circles, ellipses, rectangles, and triangles.
  arXiv  Detail & Related papers  (2024-06-30T15:48:57Z)
• Latent diffusion models for parameterization and data assimilation of facies-based geomodels [0.0]
  Diffusion models are trained to generate new geological realizations from input fields characterized by random noise. Latent diffusion models are shown to provide realizations that are visually consistent with samples from geomodeling software.
  arXiv  Detail & Related papers  (2024-06-21T01:32:03Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Counting Phases and Faces Using Bayesian Thermodynamic Integration [77.34726150561087]
  We introduce a new approach to reconstruction of the thermodynamic functions and phase boundaries in two-parametric statistical mechanics systems. We use the proposed approach to accurately reconstruct the partition functions and phase diagrams of the Ising model and the exactly solvable non-equilibrium TASEP.
  arXiv  Detail & Related papers  (2022-05-18T17:11:23Z)
• Moser Flow: Divergence-based Generative Modeling on Manifolds [49.04974733536027]
  Moser Flow (MF) is a new class of generative models within the family of continuous normalizing flows (CNF) MF does not require invoking or backpropagating through an ODE solver during training. We demonstrate for the first time the use of flow models for sampling from general curved surfaces.
  arXiv  Detail & Related papers  (2021-08-18T09:00:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.