Oral
Pathwise Derivatives Beyond the Reparameterization Trick
Martin Jankowiak · Fritz Obermeyer

Fri Jul 13th 05:50 -- 06:00 PM @ A4

We observe that gradients computed via the reparameterization trick are in direct correspondence with solutions of the transport equation in the formalism of optimal transport. We use this perspective to compute (approximate) pathwise gradients for probability distributions not directly amenable to the reparameterization trick: Gamma, Beta, and Dirichlet. We further observe that when the reparameterization trick is applied to the Cholesky-factorized multivariate Normal distribution, the resulting gradients are suboptimal in the sense of optimal transport. We derive the optimal gradients and show that they have reduced variance in a Gaussian Process regression task. We demonstrate with a variety of synthetic experiments and stochastic variational inference tasks that our pathwise gradients are competitive with other methods.

Author Information

Martin Jankowiak (Uber AI Labs)
Fritz Obermeyer (Uber AI Labs)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors