Michael Hutchinson

Phd Student in Statistical Machine Learning at the University of Oxford

Statistics Department, University of Oxford

Hi I’m Michael! I’m interested in machine learning, particularly the Bayesian flavour.

Recently I have been working on Geometric and Equivariant Deep/Probabilistic Learning, and various COIVD-19 statistical modelling efforts.

Previously I’ve worked on Architecture Search of Bayesian Neural Networks, and Differential Privacy for Federated and Continual Bayesian Learning.

Broadly I’m interested in interface between statistical and deep learning, and trying to bring more principled statistical methods into deep learning.

I am currently a PhD student at the University of Oxford through the StatML course, supervised by Yee Whye Teh and Max Welling. Before that I completed a Masters of Engineering at the University of Cambridge, supervised by Dr Rich E. Turner.


  • Geometric Learning
  • Bayesian Machine Learning
  • Climbing, Hockey, Rowing
  • Reading Fiction and Philosophy


  • PhD in Statistical Machine Learning, 2019-2023

    University College, University of Oxford

  • MEng in Information and Computer Engineering, 2018-2019

    Christs College, University of Cambridge

  • BA in Engineering, 2015-2018

    Christs College, University of Cambridge

Recent Posts

Machine Learning Summer School 2020

A collection of things related to me for, and things from, the 2020 Virtual MLSS

Differential Privacy, Approximate Bayesian Inference and Distributed Learning

Learning Private, Bayesian Machine Learning Models in the Federating Learning Context


Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Equivariant Projected Kernels

Efficient Bayesian Inference of Instantaneous Re-production Numbers at Fine Spatial Scales, with an Application to Mapping and Nowcasting the Covid-19 Epidemic in British Local Authorities

LieTransformer: Equivariant self-attention for Lie Groups

Age groups that sustain resurging COVID-19 epidemics in the United States

Technical Document 3: Effectiveness and Resource Requirements of Test, Trace and Isolate Strategies

State-level tracking of COVID-19 in the United States

Report 21: Estimating COVID-19 cases and reproduction number in Brazil

A sub-national analysis of the rate of transmission of Covid-19 in Italy

Differentially Private Federated Variational Inference