Flow-based generative model

This is an old revision of this page, as edited by TommyX12 (talk | contribs) at 07:30, 11 March 2021. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

A flow-based generative model is a statistical model that explicitly models a probability distribution by leveraging the change-of-variables law of probabilities to transform a simple distribution into a complex one. It is usually used as a generative model to learn the distribution (i.e. likelihood function) of observed data, .


Implementations

TODO description

  • RealNVP
  • TODO more items, and citation

Applications

TODO description

  • Point-cloud modeling
  • Music generation
  • TODO more items, and citation

References

TODO