Particle GFlowNets: Rethinking Generative Marginalization Models

2026-09-10

AI Summary

该研究通过将生成边缘化模型与生成流网络等同，并引入基于Gelman-Rubin统计量的状态刷新策略，加速了大组合空间中的训练过程。

Abstract

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.

Problem

• Generative Marginalization Models
• GFlowNets
• Gibbs sampler
• non-autoregressive generative processes
• Gelman-Rubin statistic

Innovation

• Particle GFlowNets
• Generative Marginalization Models
• Gelman-Rubin statistic
• non-autoregressive generation