论文标题
用于离散概率建模的生成流网络
Generative Flow Networks for Discrete Probabilistic Modeling
论文作者
论文摘要
我们提出了基于能量的生成流网络（EB-GFN），这是一种用于高维离散数据的新型概率建模算法。在生成流网络（GFLOWNETS）的理论的基础上，我们通过随机数据构建政策对生成过程进行建模，从而将昂贵的MCMC探索摊销为从Gflownet采样的固定动作中。我们展示了Gflownets如何在模式之间进行大致进行大型Gibbs采样以混合。我们提出了一个框架，以共同训练具有能量功能的Gflownet，以便Gflownet学会从能量分布中进行采样，而能量则以近似MLE目标学习，并从Gflownet中使用负样本。我们展示了EB-GFN对各种概率建模任务的有效性。代码可在https://github.com/zdhnarsil/eb_gfn上公开获取。
We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data. Building upon the theory of generative flow networks (GFlowNets), we model the generation process by a stochastic data construction policy and thus amortize expensive MCMC exploration into a fixed number of actions sampled from a GFlowNet. We show how GFlowNets can approximately perform large-block Gibbs sampling to mix between modes. We propose a framework to jointly train a GFlowNet with an energy function, so that the GFlowNet learns to sample from the energy distribution, while the energy learns with an approximate MLE objective with negative samples from the GFlowNet. We demonstrate EB-GFN's effectiveness on various probabilistic modeling tasks. Code is publicly available at https://github.com/zdhNarsil/EB_GFN.
