GFlowNet Foundations. (arXiv:2111.09266v3 [cs.LG] UPDATED)

Generative Flow Networks (GFlowNets) have been introduced as a method to
sample a diverse set of candidates in an active learning context, with a
training objective that makes them approximately sample in proportion to a
given reward function. In this paper, we show a number of additional
theoretical properties of GFlowNets. They can be used to estimate joint
probability distributions and the corresponding marginal distributions where
some variables are unspecified and, of particular interest, can represent
distributions over composite objects …

arxiv lg