Mila > Team > Frank Wood

Frank Wood

Associate Academic Member
Associate Professor, University of British Columbia, Canada CIFAR AI Chair

Frank Wood is Associate Professor of Computer Science at the University of British Columbia, and Chair in AI CIFAR-Canada at Mila. His research interests include probabilistic programming, as well as automatic learning and probabilistic artificial intelligence. He is particularly interested in Bayesian methods and unsupervised learning.

Publications

2021-09

Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation
Adam Scibior, Vasileios Lioutas, Daniele Reda, Peyman Bateni and Frank Wood

2021-07

Sequential Core-Set Monte Carlo
Boyan Beronov, Christian Weilbach, Frank Wood and Trevor Campbell
UAI 2021
(2021-07-27)
www.auai.org
q-Paths: Generalizing the Geometric Annealing Path using Power Means
Vaden W Masrani, Rob Brekelmans, Thang D Bui, Frank Nielsen, Aram Galstyan, Greg Ver Steeg and Frank Wood
Robust Asymmetric Learning in POMDPs
Andrew Warrington, Jonathan Lavington, Adam Scibior, Mark Schmidt and Frank Wood
ICML 2021
(2021-07-18)
proceedings.mlr.pressPDF
Assisting the Adversary to Improve GAN Training
Andreas Munk, William Harvey and Frank Wood

2021-06

Differentiable Particle Filtering without Modifying the Forward Pass.
Adam Scibior, Vaden Masrani and Frank Wood
arXiv preprint arXiv:2106.10314
(2021-06-18)
dblp.uni-trier.dePDF

2021-05

Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks
William Harvey, Michael Teng and Frank Wood
(venue unknown)
(2021-05-04)
openreview.netPDF
Uncertainty in Neural Processes
Saeid Naderiparizi, Kenny Chiu, Benjamin Bloem-Reddy and Frank Wood
arXiv e-prints
(2021-05-04)
ui.adsabs.harvard.eduPDF
Improving Few-Shot Visual Classification with Unlabelled Examples
Peyman Bateni, Jarred Barber, Jan-Willem van de Meent and Frank Wood
(venue unknown)
(2021-05-04)
dblp.uni-trier.dePDF

2021-02

Image Completion via Inference in Deep Generative Models
William Harvey, Saeid Naderiparizi and Frank Wood
arXiv preprint arXiv:2102.12037
(2021-02-24)
ui.adsabs.harvard.eduPDF

2020-12

Robust Asymmetric Learning in POMDPs.
Andrew Warrington, J. Wilder Lavington, Adam Åšcibior, Mark Schmidt and Frank Wood
arXiv preprint arXiv:2012.15566
(2020-12-31)
ui.adsabs.harvard.eduPDF
Annealed Importance Sampling with q-Paths.
Rob Brekelmans, Vaden Masrani, Thang Bui, Frank Wood, Aram Galstyan, Greg Ver Steeg and Frank Nielsen
arXiv preprint arXiv:2012.07823
(2020-12-14)
ui.adsabs.harvard.eduPDF
Ensemble Squared: A Meta AutoML System.
Jason Yoo, Tony Joseph, Dylan Yung, S. Ali Nasseri and Frank Wood
arXiv preprint arXiv:2012.05390
(2020-12-10)
ui.adsabs.harvard.eduPDF

2020-11

All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference.
Rob Brekelmans, Vaden Masrani, Frank Wood, Greg Ver Steeg and Aram Galstyan

2020-07

All in the (Exponential) Family: Information Geometry and Thermodynamic Variational Inference
Robert Brekelmans, Vaden W Masrani, Frank Wood, Greg Ver Steeg and Aram Galstyan
ICML 2020
(2020-07-12)
icml.cc

2020-06

Semi-supervised Sequential Generative Models
Michael Teng, Tuan Anh Le, Adam Scibior and Frank Wood
Enhancing Few-Shot Image Classification with Unlabelled Examples
Peyman Bateni, Jarred Barber, Jan-Willem van de Meent and Frank Wood
arXiv: Computer Vision and Pattern Recognition
(2020-06-17)
128.84.4.27PDF
Improved Few-Shot Visual Classification
Peyman Bateni, Raghav Goyal, Vaden Masrani, Frank Wood and Leonid Sigal
Structured Conditional Continuous Normalizing Flows for Efficient Amortized Inference in Graphical Models.
Christian Weilbach, Boyan Beronov, Frank Wood and William Harvey
AISTATS 2020
(2020-06-03)
proceedings.mlr.pressPDF
Coping With Simulators That Don't Always Return.
Andrew Warrington, Saeid Naderiparizi and Frank Wood

2020-03

Planning as Inference in Epidemiological Models
Frank Wood, Andrew Warrington, Saeid Naderiparizi, Christian Weilbach, Vaden Masrani, William Harvey, Adam Scibior, Boyan Beronov and Ali Nasseri
arXiv preprint arXiv:2003.13221
(2020-03-30)
europepmc.orgPDF

2020-01

Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
Vu Nguyen, Vaden Masrani, Rob Brekelmans, Michael A. Osborne and Frank Wood
Target–Aware Bayesian Inference: How to Beat Optimal Conventional Estimators
Tom Rainforth, Adam Golinski, Frank Wood and Sheheryar Zaidi
Journal of Machine Learning Research
(2020-01-01)
jmlr.csail.mit.eduPDF

2019-11

Etalumis: bringing probabilistic programming to scientific simulators at scale
Atilim 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 and Frank Wood
Etalumis: bringing probabilistic programming to scientific simulators at scale
Atilim 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 and Frank Wood
HIPC 2019
(2019-11-17)
inspirehep.net

2019-10

Attention for Inference Compilation
William Harvey, Andreas Munk, Atilim Günes Baydin, Alexander Bergholm and Frank Wood
arXiv preprint arXiv:1910.11961
(2019-10-25)
ui.adsabs.harvard.eduPDF
Deep Probabilistic Surrogate Networks for Universal Simulator Approximation
Andreas Munk, Adam Scibior, Atilim Günes Baydin, Andrew Stewart, Goran Fernlund, Anoush Poursartip and Frank Wood
arXiv preprint arXiv:1910.11950
(2019-10-25)
www.cs.ox.ac.ukPDF
Amortized Rejection Sampling in Universal Probabilistic Programming
Saeid Naderiparizi, Adam Scibior, Andreas Munk, Mehrdad Ghadiri, Atilim Günes Baydin, Bradley Gram-Hansen, Christian Schröder de Witt, Robert Zinkov, Philip H. S. Torr, Tom Rainforth, Yee Whye Teh and Frank Wood
arXiv preprint arXiv:1910.09056
(2019-10-20)
ui.adsabs.harvard.eduPDF
Efficient Bayesian Inference for Nested Simulators
Bradley Gram-Hansen, Christian Schroeder de Witt, Robert Zinkov, Saeid Naderiparizi, Adam Scibior, Andreas Munk, Frank Wood, Mehrdad Ghadiri, Philip Torr, Yee Whye Teh, Atilim Gunes Baydin and Tom Rainforth
(venue unknown)
(2019-10-16)
openreview.netPDF
Efficient Inference Amortization in Graphical Models using Structured Continuous Conditional Normalizing Flows
Christian Weilbach, Boyan Beronov, William Harvey and Frank Wood
(venue unknown)
(2019-10-16)
openreview.netPDF

2019-09

Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
Renhao Wang, Adam Scibior and Frank Wood
arXiv preprint arXiv:1909.09721
(2019-09-20)
ui.adsabs.harvard.eduPDF
The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging.
Andrew Warrington, Arthur Spencer and Frank Wood
arXiv preprint arXiv:1907.11075
(2019-09-11)
dblp.uni-trier.dePDF

2019-06

The Thermodynamic Variational Objective
Vaden Masrani, Tuan Anh Le and Frank Wood
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training.
William Harvey, Michael Teng and Frank Wood
arXiv preprint arXiv:1906.05462
(2019-06-13)
ui.adsabs.harvard.eduPDF

2019-05

Amortized Monte Carlo Integration
Adam Golinski, Frank Wood and Tom Rainforth

2019-04

LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models
Yuan Zhou, Bradley J. Gram-Hansen, Tobias Kohn, Tom Rainforth, Hongseok Yang and Frank Wood

2019-03

Imitation Learning of Factored Multi-agent Reactive Models
Michael Teng, Tuan Anh Le, Adam Scibior and Frank Wood
arXiv: Learning
(2019-03-12)
ui.adsabs.harvard.eduPDF

2019-01

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Atilim Gunes Baydin, Lei Shao, Wahid Bhimji, Lukas Alexander Heinrich, Saeid Naderiparizi, Andreas Munk, Jialin Liu, Bradley Gram-Hansen, Gilles Louppe, Lawrence Meadows, Philip H. S. Torr, Victor W. Lee, Kyle Cranmer, Prabhat and Frank Wood
NEURIPS 2019
(2019-01-01)
papers.nips.ccPDF
Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow.
Tuan Anh Le, Adam R. Kosiorek, N. Siddharth, Yee Whye Teh and Frank Wood

2018-12

Faithful Inversion of Generative Models for Effective Amortized Inference
Stefan Webb, Adam Golinski, Rob Zinkov, Siddharth Narayanaswamy, Tom Rainforth, Yee Whye Teh and Frank Wood
NEURIPS 2018
(2018-12-03)
papers.nips.ccPDF
Bayesian Distributed Stochastic Gradient Descent
Michael Teng and Frank Wood
NEURIPS 2018
(2018-12-03)
papers.nips.ccPDF

2018-09

Revisiting Reweighted Wake-Sleep
Tuan Anh Le, Adam R. Kosiorek, N. Siddharth, Yee Whye Teh and Frank Wood
arXiv: Machine Learning
(2018-09-27)
dblp.uni-trier.dePDF
An Introduction to Probabilistic Programming
Jan-Willem van de Meent, Brooks Paige, Hongseok Yang and Frank Wood
arXiv preprint arXiv:1809.10756
(2018-09-27)
publications.eng.cam.ac.ukPDF

2018-07

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Atılım Güneş Baydin, Lukas Heinrich, Wahid Bhimji, Lei Shao, Saeid Naderiparizi, Andreas Munk, Jialin Liu, Bradley Gram-Hansen, Gilles Louppe, Lawrence Meadows, Philip Torr, Victor Lee, Prabhat, Kyle Cranmer and Frank Wood
arXiv: Learning
(2018-07-20)
ui.adsabs.harvard.eduPDF
On Nesting Monte Carlo Estimators
Tom Rainforth, Robert Cornish, Hongseok Yang, Andrew Warrington and Frank Wood
ICML 2018
(2018-07-03)
proceedings.mlr.pressPDF
Tighter Variational Bounds are Not Necessarily Better
Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J. Maddison, Maximilian Igl, Frank Wood and Yee Whye Teh
ICML 2018
(2018-07-03)
proceedings.mlr.pressPDF

2018-06

Inference Trees: Adaptive Inference with Exploration
Tom Rainforth, Yuan Zhou, Xiaoyu Lu, Yee Whye Teh, Frank Wood, Hongseok Yang and Jan-Willem van de Meent
arXiv preprint arXiv:1806.09550
(2018-06-25)
ui.adsabs.harvard.eduPDF
Deep Variational Reinforcement Learning for POMDPs
Maximilian Igl, Luisa M. Zintgraf, Tuan Anh Le, Frank Wood and Shimon Whiteson

2018-04

Discontinuous Hamiltonian Monte Carlo for Probabilistic Programs.
Bradley Gram-Hansen, Yuan Zhou, Tobias Kohn, Hongseok Yang and Frank D. Wood
(venue unknown)
(2018-04-07)
dblp.uni-trier.dePDF
Hamiltonian Monte Carlo for Probabilistic Programs with Discontinuities
Bradley Gram-Hansen, Yuan Zhou, Tobias Kohn, Tom Rainforth, Hongseok Yang and Frank Wood
arXiv preprint arXiv:1804.03523
(2018-04-07)
ui.adsabs.harvard.eduPDF

Publications collected and formatted using Paperoni