PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise

arXiv:2403.08216v1 Announce Type: new
Abstract: Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues, which are manifold and discrete data. If the target distribution is a manifold, which means the dimension of the latent target distribution and the dimension of the data distribution are unmatched, flow-based models might perform badly. Discrete data makes flow-based models collapse into a degenerate mixture of point masses. In this paper, to sidestep such two issues we propose …

abstract arxiv cs.cv cs.lg data distribution flow generative generative modeling however manifold modeling noise padding sampling type