AI RESEARCH
On Divergence Measures for Training GFlowNets
arXiv CS.AI
•
ArXi:2410.09355v2 Announce Type: cross Generative Flow Networks (GFlowNets) are amortized inference models designed to sample from unnormalized distributions over composable objects, with applications in generative modeling for tasks in fields such as causal discovery, NLP, and drug discovery. Traditionally, the