Chris J. Maddison

Publications

• Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions
  Daniel D. Johnson, Ayoub El Hanchi, Chris J. Maddison
  ICLR, 2023
  [arXiv]
• Stochastic Reweighted Gradient Descent
  Ayoub El Hanchi, David Stephens, Chris J. Maddison
  ICML, 2022
  [arXiv]
• Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning
  Max B Paulus, Giulia Zarpellon, Andreas Krause, Laurent Charlin, Chris J. Maddison
  ICML, 2022
  [arXiv]
• Augment with Care: Contrastive Learning for the Boolean Satisfiability Problem
  Haonan Duan, Pashootan Vaezipoor, Max B. Paulus, Yangjun Ruan, Chris J. Maddison
  ICML, 2022
  [arXiv]
• Bayesian Nonparametrics for Offline Skill Discovery
  Valentin Villecroze, Harry J. Braviner, Panteha Naderian, Chris J. Maddison, Gabriel Loaiza-Ganem
  ICML, 2022
  [arXiv]
• Optimal Representations for Covariate Shift
  Yangjun Ruan*, Yann Dubois*, Chris J. Maddison
  ICLR, 2022
  [arXiv]
• Lossy Compression for Lossless Prediction
  Yann Dubois, Benjamin Bloem-Reddy, Karen Ullrich, Chris J. Maddison
  NeurIPS, 2021, Spotlight presentation
  [arXiv]
• Learning Generalized Gumbel-max Causal Mechanisms
  Guy Lorberbom*, Daniel D. Johnson*, Chris J. Maddison, Daniel Tarlow, Tamir Hazan
  NeurIPS, 2021, Spotlight presentation
  [arXiv]
• Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
  Yangjun Ruan*, Karen Ullrich*, Daniel Severo*, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani,
  Chris J. Maddison
  ICML, 2021, Long presentation
  [arXiv]
• Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
  Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
  ICML, 2021, Outstanding Paper Award Honorable Mention
  [arXiv]
• Dual Space Preconditioning for Gradient Descent
  Chris J. Maddison*, Daniel Paulin*, Yee Whye Teh, Arnaud Doucet
  SIAM Journal on Optimization, 2021
  [arXiv] [SIAM]
• Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator
  Max B. Paulus, Chris J. Maddison, Andreas Krause
  ICLR, 2021, Oral presentation
  [arXiv]
• Learning Branching Heuristics for Propositional Model Counting
  Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Chris J. Maddison, Roger Grosse, Edward Lee, Sanjit A. Seshia, Fahiem Bacchus
  AAAI, 2021
  [arXiv]
• Gradient Estimation with Stochastic Softmax Tricks
  Max B. Paulus*, Dami Choi*, Daniel Tarlow, Andreas Krause, Chris J. Maddison
  NeurIPS, 2020, Oral presentation
  [arXiv]
• Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
  Guy Lorberbom, Chris J. Maddison, Nicolas Heess, Tamir Hazan, Daniel Tarlow
  NeurIPS, 2020
  [arXiv]
• Hamiltonian descent for composite objectives
  Brendan O'Donoghue, Chris J. Maddison
  NeurIPS, 2019
  [arXiv]
• Hierarchical Representations with Poincaré Variational Auto-Encoders
  Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, Yee Whye Teh
  NeurIPS, 2019
  [arXiv]
• Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
  George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison
  ICLR, 2019
  [arXiv]
• Conditional Neural Processes
  Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami
  ICML, 2018
  [arXiv]
• Tighter Variational Bounds are Not Necessarily Better
  Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J. Maddison, Maximilian Igl, Frank Wood, Yee Whye Teh
  ICML, 2018
  [arXiv] [bibtex]
• Filtering Variational Objectives
  Chris J. Maddison*, Dieterich Lawson*, George Tucker*, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet, Yee Whye Teh
  NeurIPS, 2017
  [arXiv] [bibtex]
• REBAR : Low-variance, unbiased gradient estimates for discrete latent variable models
  George Tucker, Andriy Mnih, Chris J. Maddison, Jascha Sohl-Dickstein
  NeurIPS, 2017, Oral presentation
  [arXiv] [bibtex]
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
  Chris J. Maddison, Andriy Mnih, and Yee Whye Teh
  ICLR, 2017
  [arXiv] [bibtex]
• Mastering the game of Go with deep neural networks and tree search
  David Silver*, Aja Huang*, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, and Demis Hassabis
  Nature, Vol. 529, 484-489, 2016
  [Nature] [bibtex] [DeepMind AlphaGo]
• Move Evaluation in Go Using Deep Convolutional Neural Networks
  Chris J. Maddison, Aja Huang, Ilya Sutskever, and David Silver
  ICLR, 2015
  [pdf] [bibtex] [sgf]
• A* Sampling
  Chris J. Maddison, Daniel Tarlow, and Tom Minka
  NeurIPS, 2014, Outstanding Paper Award
  [arXiv] [bibtex] [pdf] [supplementary] [code]
• Structured Generative Models of Natural Source Code
  Chris J. Maddison and Daniel Tarlow
  ICML, 2014
  [pdf] [bibtex] [supplementary]
• Annealing Between Distributions by Averaging Moments
  Roger Grosse, Chris J. Maddison, and Ruslan Salakhutdinov
  NeurIPS, 2013, Oral presentation
  [pdf] [bibtex] [supplementary] [RBM weights as .npz]
• Soft song during aggressive interactions: Seasonal changes and endocrine correlates in song sparrows
  Chris J. Maddison, Rindy C. Anderson, Nora H. Prior, Matthew D. Taves, Kiran K. Soma
  Hormones and Behaviour, 2012
  [article]
• Rapid and Widespread Effects of 17-beta-estradiol on Intracellular Signaling in the Male Songbird Brain
  Sarah A. Heimovics, Nora H. Prior, Chris J. Maddison, Kiran K. Soma
  Endocrinology, 2012
  [article]

Book Chapters

• Current Interpretability/Explainability Techniques in AI
  Chris J. Maddison
  Responsible AI: A Global Policy Framework. C. Morgan (Ed.), 2019.
  
• A Poisson process model for Monte Carlo
  Chris J. Maddison
  Perturbation, Optimization, and Statistics. T. Hazan, G. Papandreou, D. Tarlow (Eds.), 2016.
  [pdf] [bibtex]

Workshop Presentations

• Twisted Variational Sequential Monte Carlo
  Dieterich Lawson, George Tucker, Christian Naesseth, Chris J. Maddison, Ryan Adams, Yee Whye Teh
  Bayesian Deep Learning Workshop, NeurIPS, 2018
  [pdf]
• Particle Value Functions
  Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh
  ICLR Workshop, 2017
  [arXiv]

Preprints

• On Empirical Comparisons of Optimizers for Deep Learning
  Dami Choi, Christopher J. Shallue, Zachary Nado, Jaehoon Lee, Chris J. Maddison, George E. Dahl
  [arXiv]
• Hamiltonian Descent Methods
  Chris J. Maddison*, Daniel Paulin*, Yee Whye Teh, Brendan O'Donoghue, Arnaud Doucet
  [arXiv]

* indicates equal contribution.