SOURCE-LINKED INTELLIGENCE

Particle GFlowNets: Rethinking Generative Marginalization Models

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Generative Marginalization Models (MaMs) have been recently introduced as efficient neural sampling models for any-order autoregressive modelling of discrete distributions. By learning both the marginal and conditional probabilities of a persistent-block Gibbs sampler, MaMs enable fast posterior evaluation with a single neural network forward pass. While prior work has considered MaMs to be distinct from Generative Flow Networks (GFlowNets), a well-established paradigm for inference in discrete stochastic models, we show that they are equivalent. Then, we also extend MaMs' sampling strategy to

Read original source ↗ Open in workspace

recordType

paper

region

Global