572 citations · 2k across the 30 of their papers we have counts for
4 papers · 1 filter
Closed Form Variational Objectives For Bayesian Neural Networks with a Single Hidden Layer
Martin Jankowiak
In this note we consider setups in which variational objectives for Bayesian neural networks can be computed in closed form. In particular we focus on single-layer networks in whic…
Pyro: Deep Universal Probabilistic Programming
Eli Bingham, Jonathan P. Chen, Martin Jankowiak +7
Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research. To scale to large datasets and high-dimensio…
Pathwise Derivatives Beyond the Reparameterization Trick
Martin Jankowiak, Fritz Obermeyer
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…
Pathwise Derivatives for Multivariate Distributions
Martin Jankowiak, Theofanis Karaletsos
We exploit the link between the transport equation and derivatives of expectations to construct efficient pathwise gradient estimators for multivariate distributions. We focus on t…