Generative Modeling With Bayesian Sample Inference

MCML Authors

Marcel Kollovieh

→ Group Stephan Günnemann
 Data Analytics & Machine Learning

Stephan Günnemann

Prof. Dr.

Core PI

Data Analytics & Machine Learning

Abstract

We present a novel view of diffusion-like generative modeling from the perspective of iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we formulate the sampling process in the language of Bayesian probability: at each step, a model predicts the unknown sample from our current belief state and we compute a posterior belief from that prediction. Based on this formulation, we propose the generative model Bayesian Sample Inference (BSI). In addition to a rigorous theoretical analysis, we show that our perspective includes Bayesian Flow Networks (BFNs) and that BSI and BFNs represent the two opposite ends of a range of isotropic hyper-priors over the initial belief state. In our experiments, we demonstrate that BSI improves sample quality over both BFNs and the closely related Variational Diffusion Models on ImageNet32 and ImageNet64, while achieving equivalent log-likelihoods on both datasets.

article LKG26

---

Transactions on Machine Learning Research

Vol. 2026. Aug. 2026.

---

Authors

M. Lienen • M. Kollovieh • S. Günnemann

---

Links

URL GitHub

---

Research Area

 A3 | Computational Models