Principled Interpolation in Normalizing Flows

22 Oct 2020  ·  Samuel G. Fadel, Sebastian Mair, Ricardo da S. Torres, Ulf Brefeld ·

Generative models based on normalizing flows are very successful in modeling complex data distributions using simpler ones. However, straightforward linear interpolations show unexpected side effects, as interpolation paths lie outside the area where samples are observed. This is caused by the standard choice of Gaussian base distributions and can be seen in the norms of the interpolated samples. This observation suggests that correcting the norm should generally result in better interpolations, but it is not clear how to correct the norm in an unambiguous way. In this paper, we solve this issue by enforcing a fixed norm and, hence, change the base distribution, to allow for a principled way of interpolation. Specifically, we use the Dirichlet and von Mises-Fisher base distributions. Our experimental results show superior performance in terms of bits per dimension, Fr\'echet Inception Distance (FID), and Kernel Inception Distance (KID) scores for interpolation, while maintaining the same generative performance.

PDF Abstract
No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.