paper-with-me

Papers

Reducing Memorisation in Generative Models via Riemannian Bayesian Inference

2026-01-30 · Johanna Marie Gegenfurtner, Albert Kjøller Jacobsen, Naima Elosegui Borras, Alejandro Valverde Mahou, Georgios Arvanitidis arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.00199

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Inference

Similar Papers 제목 키워드 기반

Riemannian Stein Variational Gradient Descent for Bayesian Inference

2017-11-30 · Chang Liu, Jun Zhu

We develop Riemannian Stein Variational Gradient Descent (RSVGD), a Bayesian inference method that generalizes Stein Variational Gradient Descent (SVGD) to Riemann manifold. The benefits are two-folds: (i) for inference …

Bayesian Inference

Functional Bayesian Neural Networks for Model Uncertainty Quantification

2019-05-01 · ICLR 2019 5 · Nanyang Ye, Zhanxing Zhu

In this paper, we extend the Bayesian neural network to functional Bayesian neural network with functional Monte Carlo methods that use the samples of functionals instead of samples of networks' parameters for inference …

Uncertainty Quantification

Geometric Ergodicity in Modified Variations of Riemannian Manifold and Lagrangian Monte Carlo

2023-01-04 · James A. Brofos, Vivekananda Roy, Roy R. Lederman

Riemannian manifold Hamiltonian (RMHMC) and Lagrangian Monte Carlo (LMC) have emerged as powerful methods of Bayesian inference. Unlike Euclidean Hamiltonian Monte Carlo (EHMC) and the Metropolis-adjusted Langevin algori…

Bayesian Inference

Implicit representation priors meet Riemannian geometry for Bayesian robotic grasping

2023-04-18 · Norman Marlier, Julien Gustin, Olivier Brüls, Gilles Louppe

Robotic grasping in highly noisy environments presents complex challenges, especially with limited prior knowledge about the scene. In particular, identifying good grasping poses with Bayesian inference becomes difficult…

Bayesian InferenceRobotic Grasping

The equivalence between Stein variational gradient descent and black-box variational inference

2020-04-04 · ICLR Workshop DeepDiffEq 2019 12 · Casey Chu, Kentaro Minami, Kenji Fukumizu

We formalize an equivalence between two popular methods for Bayesian inference: Stein variational gradient descent (SVGD) and black-box variational inference (BBVI). In particular, we show that BBVI corresponds precisely…

Bayesian InferenceVariational Inference