Corpus ID: 49657329

Glow: Generative Flow with Invertible 1x1 Convolutions

@article{Kingma2018GlowGF,
  title={Glow: Generative Flow with Invertible 1x1 Convolutions},
  author={Diederik P. Kingma and P. Dhariwal},
  journal={ArXiv},
  year={2018},
  volume={abs/1807.03039}
}

Diederik P. Kingma, P. Dhariwal

Published 2018

Mathematics, Computer Science

ArXiv

Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this paper we propose Glow, a simple type of generative flow using an invertible 1x1 convolution. Using our method we demonstrate a significant improvement in log-likelihood on standard benchmarks. Perhaps most strikingly, we demonstrate that a generative model… CONTINUE READING

View PDF on ArXiv

Save to Library

Create Alert

Cite

Launch Research Feed