Reducing Memorisation in Generative Models via Riemannian Bayesian Inference

• URL: http://arxiv.org/abs/2602.00199v1
• Date: Fri, 30 Jan 2026 11:08:51 GMT
• Title: Reducing Memorisation in Generative Models via Riemannian Bayesian Inference
• Authors: Johanna Marie Gegenfurtner, Albert Kjøller Jacobsen, Naima Elosegui Borras, Alejandro Valverde Mahou, Georgios Arvanitidis,
• Abstract summary: We build a predictive posterior that better captures the variability of the data distribution.<n>We demonstrate that the proposed approach reduces memorisation while preserving generalisation.<n>Overall, our work illustrates how considering the geometry of the loss enables effective use of the parameter space.
• Score: 40.41090345118905
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern generative models can produce realistic samples, however, balancing memorisation and generalisation remains an open problem. We approach this challenge from a Bayesian perspective by focusing on the parameter space of flow matching and diffusion models and constructing a predictive posterior that better captures the variability of the data distribution. In particular, we capture the geometry of the loss using a Riemannian metric and leverage a flexible approximate posterior that adapts to the local structure of the loss landscape. This approach allows us to sample generative models that resemble the original model, but exhibit reduced memorisation. Empirically, we demonstrate that the proposed approach reduces memorisation while preserving generalisation. Further, we provide a theoretical analysis of our method, which explains our findings. Overall, our work illustrates how considering the geometry of the loss enables effective use of the parameter space, even for complex high-dimensional generative models.

Related papers

• Riemannian AmbientFlow: Towards Simultaneous Manifold Learning and Generative Modeling from Corrupted Data [4.681760167323748]
  We introduce a framework for learning a probabilistic generative model and the underlying, nonlinear data manifold directly from corrupted observations.<n>We establish theoretical guarantees showing that, under appropriate geometric regularization and measurement conditions, the learned model recovers the underlying data distribution up to a controllable error and yields a smooth, bi-Lipschitz manifold parametrization.
  arXiv  Detail & Related papers  (2026-01-26T17:51:52Z)
• One-for-More: Continual Diffusion Model for Anomaly Detection [63.50488826645681]
  Anomaly detection methods utilize diffusion models to generate or reconstruct normal samples when given arbitrary anomaly images.<n>Our study found that the diffusion model suffers from severe faithfulness hallucination'' and catastrophic forgetting''<n>We propose a continual diffusion model that uses gradient projection to achieve stable continual learning.
  arXiv  Detail & Related papers  (2025-02-27T07:47:27Z)
• A solvable model of learning generative diffusion: theory and insights [44.979670733807694]
  We consider the problem of learning a flow or diffusion-based generative model parametrized by a two-layer auto-encoder.<n>We derive a tight characterization of low-dimensional projections of the distribution of samples generated by the learned model.
  arXiv  Detail & Related papers  (2025-01-07T16:56:40Z)
• Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory [9.771997770574947]
  We analyze how model reconstruction using counterfactuals can be improved. Our main contribution is to derive novel theoretical relationships between the error in model reconstruction and the number of counterfactual queries.
  arXiv  Detail & Related papers  (2024-05-08T18:52:47Z)
• Performative Prediction with Bandit Feedback: Learning through Reparameterization [23.039885534575966]
  performative prediction is a framework for studying social prediction in which the data distribution itself changes in response to the deployment of a model. We develop a reparametization that reparametrizes the performative prediction objective as a function of induced data distribution.
  arXiv  Detail & Related papers  (2023-05-01T21:31:29Z)
• Variational Laplace Autoencoders [53.08170674326728]
  Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. We present a novel approach that addresses the limited posterior expressiveness of fully-factorized Gaussian assumption. We also present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models.
  arXiv  Detail & Related papers  (2022-11-30T18:59:27Z)
• 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)
• Riemannian Score-Based Generative Modeling [56.20669989459281]
  We introduce score-based generative models (SGMs) demonstrating remarkable empirical performance. Current SGMs make the underlying assumption that the data is supported on a Euclidean manifold with flat geometry. This prevents the use of these models for applications in robotics, geoscience or protein modeling.
  arXiv  Detail & Related papers  (2022-02-06T11:57:39Z)
• GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning [54.291331971813364]
  offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
  arXiv  Detail & Related papers  (2021-02-22T19:42:40Z)
• Generative Model without Prior Distribution Matching [26.91643368299913]
  Variational Autoencoder (VAE) and its variations are classic generative models by learning a low-dimensional latent representation to satisfy some prior distribution. We propose to let the prior match the embedding distribution rather than imposing the latent variables to fit the prior.
  arXiv  Detail & Related papers  (2020-09-23T09:33:24Z)

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.