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 Frank Wood

Image Completion via Inference in Deep Generative Models


Feb 24, 2021
William Harvey, Saeid Naderiparizi, Frank Wood

* 19 pages, 12 figures 

  Access Paper or Ask Questions

Robust Asymmetric Learning in POMDPs


Dec 31, 2020
Andrew Warrington, J. Wilder Lavington, Adam Scibior, Mark Schmidt, Frank Wood


  Access Paper or Ask Questions

Annealed Importance Sampling with q-Paths


Dec 14, 2020
Rob Brekelmans, Vaden Masrani, Thang Bui, Frank Wood, Aram Galstyan, Greg Ver Steeg, Frank Nielsen

* NeurIPS Workshop on Deep Learning through Information Geometry (Best Paper Award) 

  Access Paper or Ask Questions

Ensemble Squared: A Meta AutoML System


Dec 10, 2020
Jason Yoo, Tony Joseph, Dylan Yung, S. Ali Nasseri, Frank Wood


  Access Paper or Ask Questions

Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective


Oct 31, 2020
Vu Nguyen, Vaden Masrani, Rob Brekelmans, Michael A. Osborne, Frank Wood

* NeurIPS 2020 

  Access Paper or Ask Questions

Gaussian Process Bandit Optimization of theThermodynamic Variational Objective


Oct 29, 2020
Vu Nguyen, Vaden Masrani, Rob Brekelmans, Michael A. Osborne, Frank Wood

* NeurIPS 2020 

  Access Paper or Ask Questions

Uncertainty in Neural Processes


Oct 08, 2020
Saeid Naderiparizi, Kenny Chiu, Benjamin Bloem-Reddy, Frank Wood


  Access Paper or Ask Questions

Assisting the Adversary to Improve GAN Training


Oct 03, 2020
Andreas Munk, William Harvey, Frank Wood


  Access Paper or Ask Questions

All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference


Jul 01, 2020
Rob Brekelmans, Vaden Masrani, Frank Wood, Greg Ver Steeg, Aram Galstyan

* ICML 2020 

  Access Paper or Ask Questions

Semi-supervised Sequential Generative Models


Jun 30, 2020
Michael Teng, Tuan Anh Le, Adam Scibior, Frank Wood

* Accepted to Uncertainty in Artificial Intelligence 2020 

  Access Paper or Ask Questions

Improving Few-Shot Visual Classification with Unlabelled Examples


Jun 17, 2020
Peyman Bateni, Jarred Barber, Jan-Willem van de Meent, Frank Wood


  Access Paper or Ask Questions

Planning as Inference in Epidemiological Models


Apr 03, 2020
Frank Wood, Andrew Warrington, Saeid Naderiparizi, Christian Weilbach, Vaden Masrani, William Harvey, Adam Scibior, Boyan Beronov, Ali Nasseri

* minor typos corrected 

  Access Paper or Ask Questions

Coping With Simulators That Don't Always Return


Mar 28, 2020
Andrew Warrington, Saeid Naderiparizi, Frank Wood

* AISTATS 2020 camera ready, version 1.0 

  Access Paper or Ask Questions

Improved Few-Shot Visual Classification


Dec 12, 2019
Peyman Bateni, Raghav Goyal, Vaden Masrani, Frank Wood, Leonid Sigal


  Access Paper or Ask Questions

Amortized Rejection Sampling in Universal Probabilistic Programming


Nov 30, 2019
Saeid Naderiparizi, Adam Ścibior, Andreas Munk, Mehrdad Ghadiri, Atılım Güneş Baydin, Bradley Gram-Hansen, Christian Schroeder de Witt, Robert Zinkov, Philip H. S. Torr, Tom Rainforth, Yee Whye Teh, Frank Wood


  Access Paper or Ask Questions

Attention for Inference Compilation


Oct 25, 2019
William Harvey, Andreas Munk, Atılım Güneş Baydin, Alexander Bergholm, Frank Wood


  Access Paper or Ask Questions

Deep Probabilistic Surrogate Networks for Universal Simulator Approximation


Oct 25, 2019
Andreas Munk, Adam Ścibior, Atılım Güneş Baydin, Andrew Stewart, Goran Fernlund, Anoush Poursartip, Frank Wood


  Access Paper or Ask Questions

Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation


Sep 20, 2019
Renhao Wang, Adam Scibior, Frank Wood

* Submitted to the 2020 International Conference on Robotics and Automation 

  Access Paper or Ask Questions

The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging


Jul 24, 2019
Andrew Warrington, Arthur Spencer, Frank Wood

* Includes Supplementary Materials 

  Access Paper or Ask Questions

Amortized Monte Carlo Integration


Jul 18, 2019
Adam Goliński, Frank Wood, Tom Rainforth

* Awarded Best Paper Honourable Mention at International Conference on Machine Learning (ICML) 2019 

  Access Paper or Ask Questions

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale


Jul 08, 2019
Atılım Güneş Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, Jialin Liu, Andreas Munk, Saeid Naderiparizi, Bradley Gram-Hansen, Gilles Louppe, Mingfei Ma, Xiaohui Zhao, Philip Torr, Victor Lee, Kyle Cranmer, Prabhat, Frank Wood

* 14 pages, 8 figures 

  Access Paper or Ask Questions

The Thermodynamic Variational Objective


Jun 28, 2019
Vaden Masrani, Tuan Anh Le, Frank Wood


  Access Paper or Ask Questions

Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training


Jun 13, 2019
William Harvey, Michael Teng, Frank Wood

* 9 pages, 5 figures + appendix with 6 pages, 4 figures.Submitted to NeurIPS 2019 

  Access Paper or Ask Questions

Imitation Learning of Factored Multi-agent Reactive Models


Mar 12, 2019
Michael Teng, Tuan Anh Le, Adam Scibior, Frank Wood


  Access Paper or Ask Questions

LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models


Mar 06, 2019
Yuan Zhou, Bradley J. Gram-Hansen, Tobias Kohn, Tom Rainforth, Hongseok Yang, Frank Wood

* Published in the proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) 

  Access Paper or Ask Questions

Faithful Inversion of Generative Models for Effective Amortized Inference


Oct 24, 2018
Stefan Webb, Adam Golinski, Robert Zinkov, N. Siddharth, Tom Rainforth, Yee Whye Teh, Frank Wood

* To appear at the 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montreal, Canada 

  Access Paper or Ask Questions

An Introduction to Probabilistic Programming


Sep 27, 2018
Jan-Willem van de Meent, Brooks Paige, Hongseok Yang, Frank Wood

* Under review at Foundations and Trends in Machine Learning 

  Access Paper or Ask Questions