id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
bracis-33548	Silva, Tiago da; Mesquita, Diego	A Contrastive Objective for Training Continuous Generative Flow Networks	2024		.htm	text/html	6445	321	51	In this context, inspired by the success of contrastive learning for variational inference, we propose the continuous contrastive loss (CCL) as the first objective function natively enabling off-policy training of continuous GFlowNets without reliance on the approximation of high-dimensional integrals via SGD, extending previous work based on discrete distributions. We derive a contrastive balance condition for continuous GFlowNets and rigorously show that it is a sufficient for ensuring sampling correctness; 2.	cache/bracis-33548.htm	txt/bracis-33548.txt