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 Chris J. Maddison

Lossy Compression for Lossless Prediction


Jul 07, 2021
Yann Dubois, Benjamin Bloem-Reddy, Karen Ullrich, Chris J. Maddison


  Access Paper or Ask Questions

Learning to Extend Program Graphs to Work-in-Progress Code


May 28, 2021
Xuechen Li, Chris J. Maddison, Daniel Tarlow


  Access Paper or Ask Questions

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding


Feb 22, 2021
Yangjun Ruan, Karen Ullrich, Daniel Severo, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani, Chris J. Maddison


  Access Paper or Ask Questions

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions


Feb 08, 2021
Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison

* Energy-Based Models, Deep generative models, MCMC sampling 

  Access Paper or Ask Questions

Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator


Oct 09, 2020
Max B. Paulus, Chris J. Maddison, Andreas Krause


  Access Paper or Ask Questions

Learning Branching Heuristics for Propositional Model Counting


Jul 07, 2020
Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Chris J. Maddison, Roger Grosse, Edward Lee, Sanjit A. Seshia, Fahiem Bacchus


  Access Paper or Ask Questions

Gradient Estimation with Stochastic Softmax Tricks


Jun 15, 2020
Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause, Chris J. Maddison


  Access Paper or Ask Questions

On Empirical Comparisons of Optimizers for Deep Learning


Oct 11, 2019
Dami Choi, Christopher J. Shallue, Zachary Nado, Jaehoon Lee, Chris J. Maddison, George E. Dahl


  Access Paper or Ask Questions

Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces


Jun 14, 2019
Guy Lorberbom, Chris J. Maddison, Nicolas Heess, Tamir Hazan, Daniel Tarlow


  Access Paper or Ask Questions

Hierarchical Representations with Poincaré Variational Auto-Encoders


Jan 17, 2019
Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, Yee Whye Teh


  Access Paper or Ask Questions

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives


Oct 09, 2018
George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison


  Access Paper or Ask Questions

Hamiltonian Descent Methods


Sep 13, 2018
Chris J. Maddison, Daniel Paulin, Yee Whye Teh, Brendan O'Donoghue, Arnaud Doucet


  Access Paper or Ask Questions

Conditional Neural Processes


Jul 04, 2018
Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami


  Access Paper or Ask Questions

Tighter Variational Bounds are Not Necessarily Better


Jun 25, 2018
Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J. Maddison, Maximilian Igl, Frank Wood, Yee Whye Teh

* To appear at ICML 2018 

  Access Paper or Ask Questions

Filtering Variational Objectives


Nov 12, 2017
Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet, Yee Whye Teh


  Access Paper or Ask Questions

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models


Nov 06, 2017
George Tucker, Andriy Mnih, Chris J. Maddison, Dieterich Lawson, Jascha Sohl-Dickstein

* NIPS 2017 

  Access Paper or Ask Questions

Particle Value Functions


Mar 16, 2017
Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh


  Access Paper or Ask Questions

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables


Mar 05, 2017
Chris J. Maddison, Andriy Mnih, Yee Whye Teh


  Access Paper or Ask Questions

Move Evaluation in Go Using Deep Convolutional Neural Networks


Apr 10, 2015
Chris J. Maddison, Aja Huang, Ilya Sutskever, David Silver

* Minor edits and included captures in Figure 2 

  Access Paper or Ask Questions

A* Sampling


Jan 26, 2015
Chris J. Maddison, Daniel Tarlow, Tom Minka

* V2: - reworded the last paragraph of Section 2 to clarify that the argmax is a sample from the normalized measure. - fixed notation in Algorithm 1. - fixed a typo in paragraph 2 of Section 5 

  Access Paper or Ask Questions

Structured Generative Models of Natural Source Code


Jun 20, 2014
Chris J. Maddison, Daniel Tarlow


  Access Paper or Ask Questions