What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models

Published: 22 Jan 2025, Last Modified: 14 Apr 2025ICLR 2025 PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Geometry, Diffusion models, VAE, Generative Models, Guidance, Memorization, Out-of-Distribution Detection
TL;DR: We show that the local geometry of generative models is indicative of generation aesthetics, artifacts, diversity, and memorization.
Abstract: Deep Generative Models are frequently used to learn continuous representations of complex data distributions by training on a finite number of samples. For any generative model, including pre-trained foundation models with Diffusion or Transformer architectures, generation performance can significantly vary across the learned data manifold. In this paper, we study the local geometry of the learned manifold and its relationship to generation outcomes for a wide range of generative models, including DDPM, Diffusion Transformer (DiT), and Stable Diffusion 1.4. Building on the theory of continuous piecewise-linear (CPWL) generators, we characterize the local geometry in terms of three geometric descriptors - scaling ($\psi$), rank ($\nu$), and complexity/un-smoothness ($\delta$). We provide quantitative and qualitative evidence showing that for a given latent vector, the local descriptors are indicative of post-generation aesthetics, generation diversity, and memorization by the generative model. Finally, we demonstrate that by training a reward model on the 'local scaling' for Stable Diffusion, we can self-improve both generation aesthetics and diversity using geometry sensitive guidance during denoising. Website: https://imtiazhumayun.github.io/generative_geometry.
Primary Area: generative models
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13284
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview