Mark Rowland | PhD Student | Cambridge University

About Me

I'm a PhD student at Clare College, Cambridge University, co-supervised by Rich Turner at the Machine Learning Group and John Aston at Statslab. My research is broadly into machine learning and computational statistics. Before starting my PhD, I studied for a BA and MMath at Cambridge. I focused mainly on Probability and Algebra courses in the final year, and wrote my Part III essay "Mixing Times of Random Transpositions" under the supervision of Nathanaël Berestycki. I worked as an actuarial consultant before starting my PhD, and during my PhD I've interned as a Quantitative Researcher at G-Research, and as a Research Scientist at DeepMind.

Research

I'm interested in many areas across machine learning, statistics, probability, and optimisation, and interactions with areas of pure maths such as group theory and optimal transport theory. To date, I've worked on areas including inference problems for discrete graphical models, Monte Carlo methods (particularly over non-Abelian groups), reinforcement learning, and probabilistic deep learning.

News

(July 2018)

I'll be at ICML 2018 in Stockholm, presenting Structured Evolution with Compact Architectures for Scalable Policy Optimisation.

An ArXiv preprint is available for our paper Antithetic and Monte Carlo Kernel Estimators for Partial Rankings.

We recently arxived an extended version of our ICLR paper Gaussian Process Behaviour in Wide Deep Neural Networks. In this newer version of the paper, we formally show that wide stochastic deep networks converge to Gaussian processes under much milder conditions than in the ICLR version.

Preprints

Gaussian Process Behaviour in Wide Deep Neural Networks
Alexander G. de G. Matthews, Mark Rowland, Jiri Hron, Richard E. Turner, Zoubin Ghahramani
Extended version of the paper appearing at ICLR 2018
[preprint]

Antithetic and Monte Carlo Kernel Estimators for Partial Rankings
Maria Lomeli, Mark Rowland, Arthur Gretton, Zoubin Ghahramani
[preprint]

Publications

Structured Evolution with Compact Architectures for Scalable Policy Optimization
Krzysztof Choromanski*, Mark Rowland*, Vikas Sindhwani, Richard E. Turner, Adrian Weller [*equal contribution]
ICML 2018
[preprint] [poster]

Gaussian Process Behaviour in Wide Deep Neural Networks
Alexander G. de G. Matthews, Jiri Hron, Mark Rowland, Richard E. Turner, Zoubin Ghahramani
ICLR 2018
[preprint]

An Analysis of Categorical Distributional Reinforcement Learning
Mark Rowland, Marc G. Bellemare, Will Dabney, Rémi Munos, Yee Whye Teh
AISTATS 2018
[preprint]

The Geometry of Random Features
Krzysztof Choromanski*, Mark Rowland*, Tamas Sarlos, Vikas Sindhwani, Richard E. Turner, Adrian Weller [*equal contribution]
AISTATS 2018
[preprint]

Distributional Reinforcement Learning with Quantile Regression
Will Dabney, Mark Rowland, Marc G. Bellemare, Rémi Munos
AAAI 2018
[paper]

Uprooting and Rerooting Higher-Order Graphical Models
Mark Rowland*, Adrian Weller* [*equal contribution]
NIPS 2017
[paper] [poster]

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings
Krzysztof Choromanski*, Mark Rowland*, Adrian Weller [*equal contribution]
NIPS 2017
[paper] [poster]

Magnetic Hamiltonian Monte Carlo
Nilesh Tripuraneni, Mark Rowland, Zoubin Ghahramani, Richard E. Turner
ICML 2017
[paper] [supplementary material] [poster]

Conditions Beyond Treewidth for Tightness of Higher-Order LP Relaxations
Mark Rowland, Aldo Pacchiano, Adrian Weller
AISTATS 2017
[paper] [supplementary material] [poster]
Also presented at the International Conference on Principles and Practices of Constraint Programming (CP 2017)

Black-box Alpha Divergence Minimization
Yingzhen Li, José Miguel Hernández-Lobato, Mark Rowland, Daniel Hernández-Lobato, Thang Bui, Richard E. Turner
ICML 2016
[paper] [supplementary material]

Tightness of LP Relaxations for Almost Balanced Models
Adrian Weller, Mark Rowland, David Sontag
AISTATS 2016
[paper] [supplementary material] [poster]
Also presented at the International Conference on Principles and Practices of Constraint Programming (CP 2016)

Teaching

I'm currently giving supervisions for Part IB Statistics, and in previous years have given supervisions on Part IA Groups, Part IA Probability, Part IB Linear Algebra, and Part IB Statistics. I gave examples classes for Part III Bayesian Modelling and Computation in Lent 2017, and run MATLAB introduction sessions for Maths Tripos students.

Selected Recent Talks

Analysing Distributional Reinforcement Learning
Microsoft Research Cambridge, February 2018

Optimal Transport for Machine Learning (with Wenbo Gong)
Cambridge MLG Reading Group, November 2017

MAP Inference in Undirected Graphical Models
Cambridge MLG Research Talk, November 2016

Tightness of LP Relaxations for Almost Balanced Models
International Conference on Principles and Practice of Constraint Programming (CP), Toulouse, September 2016

Coupling from the Past
Machine Learning Group Tea Talk, March 2016

Stochastic Approximation Theory (with Yingzhen Li)
Cambridge MLG Reading Group, November 2015

Contact

Feel free to get in touch via mr504 [ at ] cam [ dot ] ac [ dot ] uk.

My LinkedIn profile