Peter Orbanz

Welcome.

I am Professor of Machine Learning in the Gatsby Computational Neuroscience Unit at University College London. I work on machine learning, symmetry, and dynamics. Broad themes in my research are:

  • Exchangeability, stationarity, and other symmetry properties.
  • Mathematical statistics of machine learning methods.
  • The intersection of ergodic theory with learning and inference.
  • Applications of machine learning to physics and engineering, in collaboration with Ryan Adam's group at Princeton.
  • Bayesian inference and inference in random graphs.

I was a PhD student of Joachim M. Buhmann at ETH Zurich, a postdoc with Zoubin Ghahramani at the University of Cambridge, and Assistant and Associate Professor in the Department of Statistics at Columbia University. I have spent sabbaticals at the Isaac Newton Institute in Cambridge, in the Theory Group at Microsoft Research New England, and at UC Berkeley.


Research group

Hugh Dance • PhD student
Vasco Portilheiro • PhD student
Vince Velkey • PhD student

Former PhD students and postdocs

Morgane Austern • Assistant Professor • Harvard University
Benjamin Bloem-Reddy • Assistant Professor • University of British Columbia
Lee M Gunderson • Assistant Professor • University of Bath
Kevin H Huang • Postdoc • University of Warwick and Princeton University
Victor Veitch • Assistant Professor • University of Chicago
Wenda Zhou • Researcher • OpenAI