NIPS Proceedingsβ

Implicit Reparameterization Gradients

Part of: Advances in Neural Information Processing Systems 31 (NIPS 2018) pre-proceedings

[PDF] [BibTeX] [Supplemental]


Conference Event Type: Poster


By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for training a variety of latent variable models. However, it is not applicable to a number of important continuous distributions. We introduce an alternative approach to computing reparameterization gradients based on implicit differentiation and demonstrate its broader applicability by applying it to Gamma, Beta, Dirichlet, and von Mises distributions, which cannot be used with the classic reparameterization trick. Our experiments show that the proposed approach is faster and more accurate than the existing gradient estimators for these distributions.