Brian McWilliams.


I am a research scientist at Disney Research Zurich heading the Deep Learning and Analytics group. I am particularly interested in deep learning, randomized algorithms and optimization for large scale learning.

I completed my Ph.D. in 2012 in the Statistics Section of the Department of Mathematics Imperial College, London under the supervision of Giovanni Montana. Previously, I did the MSc. in Informatics specialising in Machine Learning, Neuroinformatics and Intelligent Robotics at the University of Edinburgh and a BEng. in Computer Systems Engineering at the University of Warwick.

Until August 2015 I was a postdoctoral researcher and lecturer in the Institute of Machine Learning at ETH Zurich.

Open positions: We have postdoc and internship openings for talented researchers in the fields of machine learning, optimization and statistics. Particularly in the areas of deep learning for natural language understanding and reinforcement learning. If that sounds like your thing, please get in touch.


November 2016
Neural Taylor Approximation, a new paper by David Baludzzi, Tony Butler-Yeoman and myself. TL;DR: We provide the first convergence result for rectifier neural networks.

August 2016
RadaGrad! our paper on scalable approximations to full-matrix AdaGrad using random projections is accepted to NIPS 2016!



  • Neural Taylor Approximation: Convergence and Exploration in Rectifier Networks.
    David Balduzzi, Brian McWilliams, Tony Butler-Yeoman. arXiv.
  • Preserving Differential Privacy Between Features in Distributed Estimation.
    Christina Heinze, Brian McWilliams, Nicolai Meinshausen.
  • Semi-Supervised Learning with Correlated Convolutional Networks.
    Ivan Ovinnikov, Brian McWilliams, Dmitry Laptev, Joachim Buhmann.


  • Scalable Adaptive Stochastic Optimization Using Random Projections.
    Gabriel Krummenacher, Brian McWilliams, Yannic Kilcher, Joachim Buhmann, Nicolai Meinshausen. NIPS 2016. arXiv.
  • A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation.
    Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams, Markus Gross, Luc Van Gool, Alexander Sorkine-Hornung. CVPR 2016.
    Project page.
  • DUAL-LOCO: Distributing Statistical Estimation Using Random Projections.
    Christina Heinze, Brian McWilliams, Nicolai Meinshausen. AISTATS 2016. arXiv. Software (maintained by Christina).


  • Variance Reduced Stochastic Gradient Descent with Neighbors.
    Thomas Hofmann, Aurelien Lucchi, Simon Lacoste-Julien, Brian McWilliams. NIPS 28. arXiv.
  • DUAL-LOCO: Preserving privacy between features in distributed estimation.
    Christina Heinze, Brian McWilliams, Nicolai Meinshausen. NIPS WS on Learning and privacy with incomplete data and weak supervision.
  • LOCO: Distributing Ridge Regression with Random Projections.
    Christina Heinze, Brian McWilliams, Nicolai Meinshausen, Gabriel Krummenacher. arXiv.
    Software (maintained by Christina).
  • Learning Representations for Outlier Detection on a Budget.
    Barbora Micenková, Brian McWilliams, Ira Assent. arXiv.
  • A Variance Reduced Stochastic Newton Method.
    Aurelien Lucchi, Brian McWilliams, Thomas Hofmann. arXiv.



  • Correlated random features for fast semi-supervised learning.
    With David Balduzzi, Joachim M. Buhmann. In Advances in Neural Information Processing Systems (NIPS) 26. arXiv. Matlab code. Poster.
  • Pruning random features with correlated kitchen sinks (1 page abstract).
    With David Balduzzi. SPARS 2013.

2012 and earlier


Fall Semester 2014

I co-lectured Probabilistic Graphical Models for Image Analysis with Dr. Aurelien Lucchi.

Spring Semester 2014

I was head TA of Computational Intelligence Laboratory. This course is now taught by Prof. Hofmann and headed by Martin Jaggi and Aurelien Lucchi.


The website for the probabilistic graphical models course that Dr. David Balduzzi and I taught at Uni Basel in summer 2013 is located here.



Disney Research Zurich
Stampfenbachstrasse 48
8006 Zurich