Improving and generalizing flow-based generative models with minibatch optimal transport

arXiv:2302.00482v4 Announce Type: replace
Abstract: Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their simulation-based maximum likelihood training. We introduce the generalized conditional flow matching (CFM) technique, a family of simulation-free training objectives for CNFs. CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models. In contrast to both diffusion models and prior …

abstract arxiv continuous continuous normalizing flows cs.lg family features flow free generalized generative generative modeling generative models likelihood limitations modeling simulation training transport type