A Sampling-Free Approximation of Gaussian Variational Auto-Encoders

29 Sep 2021  ·  Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen ·

We propose a sampling-free approximate formulation of Gaussian variational auto-encoders. Instead of computing the loss via stochastic sampling, we propagate the Gaussian distributions from the latent space into the output space. As computing the exact likelihood probability is intractable, we propose to locally approximate the decoder network by its Taylor series. We demonstrate that this approximation allows us to approximate the Gaussian variational auto-encoder training objective in closed form. We evaluate the proposed method on the CelebA, the 3D Chairs, and the MNIST data sets. We find that our sampling-free approximation performs better than its sampling counterpart on the Frechet inception distance and on par on the estimated marginal likelihood.

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.


No methods listed for this paper. Add relevant methods here