Chris J. Maddison
I am a DPhil student in the Statistical Machine Learning Group in the Department of Statistics at the University of Oxford supervised by Yee Whye Teh and Arnaud Doucet. I also spend two days a week as a Research Scientist at DeepMind. Previously, I received my MSc. from the University of Toronto supervised by Geoffrey Hinton. I was one of the primary contributors to the AlphaGo project. My research interests are probabilistic inference and Monte Carlo methods. My other interests include neural networks, learning in non-human animals, and probability theory.
- e-mail: username [at] stats [dot] ox [dot] ac [dot] uk
- username = cmaddis
- I've started a blog, hoping to cover topics in machine learning and statistics with a focus on cool tricks and forgotten papers.
- Perturbation, Optimization, and Statistics is out! It includes with a chapter of mine, A Poisson process model for Monte Carlo, which explains the Gumbel-Max trick and Gumbel processes through the theory of Poisson processes.
- A new distribution on the simplex applied to training discrete units in neural nets: [arxiv].
- I've moved to Oxford!
Work in progress
Filtering Variational Objectives
Particle Value Functions
REBAR : Low-variance, unbiased gradient estimates for discrete latent variable models
The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
International Conference on Learning Representations, 2017
A Poisson process model for Monte Carlo
Perturbation, Optimization, and Statistics. T. Hazan, G. Papandreou, D. Tarlow (Eds.), 2016.
Mastering the game of Go with deep neural networks and tree search
Nature, Vol. 529, 484-489, 2016
[Nature] [bibtex] [DeepMind AlphaGo]
Move Evaluation in Go Using Deep Convolutional Neural Networks
International Conference on Learning Representations, 2015
[pdf] [bibtex] [sgf]
Neural Information Processing Systems, 2014
[Oral Presentation] [Best Paper Award]
[pdf] [bibtex] [supplementary] [code]
Structured Generative Models of Natural Source Code
The 31st International Conference on Machine Learning, 2014
[pdf] [bibtex] [supplementary]
Annealing Between Distributions by Averaging Moments
Neural Information Processing Systems, 2013
[pdf] [bibtex] [supplementary] [RBM weights as .npz]
Soft song during aggressive interactions: Seasonal changes and endocrine correlates in song sparrows
Hormones and Behaviour, 2012
Rapid and Widespread Effects of 17-beta-estradiol on Intracellular Signaling in the Male Songbird Brain