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, optimisation, and computer science, and interactions with areas of pure maths such as group theory and optimal transport theory. To date, I've worked on problems including MAP inference for discrete graphical models, Monte Carlo methods, structured random features and projections, and reinforcement learning.

News

November 2017

Distributional Reinforcement Learning with Quantile Regression has been accepted to AAAI 2018.

I've added some introductory slides on Optimal Transport for Machine Learning (as part of the MLG reading group at Cambridge) - jointly written with Wenbo Gong.

Publications

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

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

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

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

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

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

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

Teaching

I'm currently giving supervisions for Part IA Groups, 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

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) - Camnridge MLG Reading Group, November 2015

Contact

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

My LinkedIn profile