{"slug": "particle-gflownets-rethinking-generative-marginalization-models", "title": "Particle GFlowNets: Rethinking Generative Marginalization Models", "summary": "A new arXiv paper (2609.11538v1) shows that Generative Marginalization Models (MaMs) are equivalent to Generative Flow Networks (GFlowNets), and introduces Particle GFlowNets, which extends MaMs' sampling strategy to non-autoregressive generative processes. The method adds an automatic criterion for full-state rejuvenation of the Gibbs sampler derived from the Gelman-Rubin statistic, which the authors report markedly accelerates training convergence in large combinatorial spaces.", "body_md": "arXiv:2609.11538v1 Announce Type: new \nAbstract: 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 non-autoregressive generative processes. In particular, we describe an automatic criterion for full-state rejuvenation of the Gibbs sampler, derived from the Gelman-Rubin statistic, which plays a key role in speeding up learning convergence. Our experiments show that our method, called Particle GFlowNets, markedly accelerates training in large combinatorial spaces.", "url": "https://wpnews.pro/news/particle-gflownets-rethinking-generative-marginalization-models", "canonical_source": "https://www.machinebrief.com/news/particle-gflownets-rethinking-generative-marginalization-mod-ibjh", "published_at": "2026-09-11 04:00:00+00:00", "updated_at": "2026-09-11 05:27:23.228068+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "generative-ai"], "entities": ["Generative Marginalization Models", "GFlowNets", "Particle GFlowNets", "Gelman-Rubin statistic", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/particle-gflownets-rethinking-generative-marginalization-models", "markdown": "https://wpnews.pro/news/particle-gflownets-rethinking-generative-marginalization-models.md", "text": "https://wpnews.pro/news/particle-gflownets-rethinking-generative-marginalization-models.txt", "jsonld": "https://wpnews.pro/news/particle-gflownets-rethinking-generative-marginalization-models.jsonld"}}