Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Geoffrey Roeder

Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework


Jun 29, 2021
Jacob Miller, Geoffrey Roeder, Tai-Danae Bradley

* 18 pages, 11 figures 

  Access Paper or Ask Questions

On Linear Identifiability of Learned Representations


Jul 08, 2020
Geoffrey Roeder, Luke Metz, Diederik P. Kingma


  Access Paper or Ask Questions

Learning Composable Energy Surrogates for PDE Order Reduction


May 15, 2020
Alex Beatson, Jordan T. Ash, Geoffrey Roeder, Tianju Xue, Ryan P. Adams


  Access Paper or Ask Questions

Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems


May 28, 2019
Geoffrey Roeder, Paul K. Grant, Andrew Phillips, Neil Dalchau, Edward Meeds

* Accepted at ICML 2019 

  Access Paper or Ask Questions

Backpropagation through the Void: Optimizing control variates for black-box gradient estimation


Feb 23, 2018
Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud

* Published at ICLR 2018 

  Access Paper or Ask Questions

Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference


May 28, 2017
Geoffrey Roeder, Yuhuai Wu, David Duvenaud


  Access Paper or Ask Questions