User Tools

Site Tools


Geometrical Insights for Implicit Generative Modeling

Abstract: Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the Maximum Mean Discrepancy criterion. A careful look at the geometries induced by these distances on the space of probability measures reveals interesting differences. In particular, we can establish surprising approximate global convergence guarantees for the 1-Wasserstein distance, even when the parametric generator has a nonconvex parametrization.

Léon Bottou, Martin Arjovsky, David Lopez-Paz and Maxime Oquab: Geometrical Insights for Implicit Generative Modeling, To appear. ArXiV:1712.07822.

geometry-2018.djvu geometry-2018.pdf geometry-2018.ps.gz

@incollection{bottou-geometry-2018,
  author = {Bottou, L{\'e}on and Arjovsky, Martin and Lopez-Paz, David and Oquab, Maxime},
  title = {Geometrical Insights for Implicit Generative Modeling},
  year = {2018},
  note = {To appear. ArXiV:1712.07822},
  url = {http://leon.bottou.org/papers/bottou-geometry-2018},
}
papers/bottou-geometry-2018.txt · Last modified: 2018/05/10 14:14 by leonb

Page Tools