Theodore Papamarkou

Theodore Papamarkou

Reader in maths of data science

The University of Manchester

Biography

I am interested in the problem of speeding up computation. My research spans approximate inference and the study of data with topological techniques, to enable computation in high dimensions. Bayesian deep learning and topological deep learning are the two main areas of my work. Details about my current projects can be found here.

The theory of computation, quantum computing and neuromorphic computing appeal to me, as they may provide computational speedup. Healthcare is the domain of application that I aspire to support with computational advancements.

Interests
  • Computing
  • Bayesian deep learning
  • Topological deep learning
  • Computing for healthcare
Education
  • PhD in statistics, 2009

    University of Warwick

  • MSc in statistics, 2005

    University of Warwick

  • BSc in mathematics, 2004

    University of Ioannina

Experience

 
 
 
 
 
Reader in the mathematics of data science
October 2020 – Present Manchester, UK
Research on Bayesian deep learning and topological deep learning. Teaching topics associated with data science. Lead of the advanced mathematics cluster of the Centre for Digital Trust and Security. Chair of the Mathematics Department forum.
 
 
 
 
 
Research scientist
April 2019 – September 2020 Oak Ridge, Tennessee, USA
Strategic hire in artificial intelligence. Principal investigator of two-year laboratory directed research and development (LDRD) project ‘Scalable Bayesian uncertainty quantification for neural networks’. Conducted research on Bayesian inference for neural networks.
 
 
 
 
 
Assistant professor in statistics
September 2015 – March 2019 Glasgow, UK
Conducted research on Markov chain Monte Carlo methodology. Taught three courses, namely ‘big data analytics’, ‘data analysis’ and ‘statistical methods’. Advisor of studies of twenty-one undergraduate students. Head of taught postgraduate programme in statistics and data analytics.
 
 
 
 
 
Research fellow in statistics
July 2014 – August 2015 Coventry, UK
Conducted research on two projects. One project was related to Bayesian modelling of single-cell RNA sequencing data. The other project was related to Bayesian inference for rough differential equations.
 
 
 
 
 
Research associate in statistics
January 2014 – June 2014 Coventry, UK
For 80% of work time, conducted research on Bayesian model selection via population Markov chain Monte Carlo for a biochemical pathway of Ewing sarcoma. For the remaining 20% of work time, administrated the UK-wide network on computational statistics and machine learning (NCSML).
 
 
 
 
 
Research associate in statistics
December 2011 – December 2013 London, UK
Conducted research on variance reduction for differential geometric Markov chain Monte Carlo methods.
 
 
 
 
 
Research associate in statistics
February 2010 – November 2011 London, UK
Performed statistical analysis of big genomic data sets to identify genetic determinants of blood lipid levels. Provided support for data filtering, bioinformatics and computing tasks.
 
 
 
 
 
Research statistician
July 2009 – October 2009 London, UK
Researched epidemiological associations between alcohol abstinence and personality disorders.

Publications

Access and search all publications.
(2023). Approximate blocked Gibbs sampling for Bayesian neural networks. In Statistics and Computing.

Cite Source Document

(2023). Depth-2 neural networks under a data-poisoning attack. In Neurocomputing.

Cite Source Document

(2022). A random persistence diagram generator. In Statistics and Computing.

Cite Source Document

(2022). Challenges in Markov chain Monte Carlo for Bayesian neural networks. In Statistical Science.

Cite Project Source Document

(2021). Distributions.jl: definition and modeling of probability distributions in the JuliaStats ecosystem. In Journal of Statistical Software.

PDF Cite Source Document

(2020). Wide neural networks with bottlenecks are deep Gaussian processes. In Journal of Machine Learning Research.

PDF Cite Code Source Document

(2018). Multiphase MCMC sampling for parameter inference in nonlinear ordinary differential equations. In Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics.

PDF Cite Source Document

(2016). The controlled thermodynamic integral for Bayesian model evidence evaluation. In Journal of the American Statistical Association.

Cite Source Document

(2016). RNA editing generates cellular subsets with diverse sequence within populations. In Nature Communications.

Cite Source Document

(2014). Zero variance differential geometric Markov chain Monte Carlo algorithms. In Bayesian Analysis.

PDF Cite Source Document

Contact