Hong Ge's Home Page

Hong Ge 

Research Fellow
Machine Learning Group
Cambridge University

Research Fellow
Darwin College, Cambridge

I am a research fellow in the Cambridge Machine Learning Group. My current work is on efficient (both computational and statistical wise) approximate inference methods for black-box style generic inference, with applications in probabilistic programming and nonparametric Bayesian learning (e.g. Dirichlet processes, fragmentation processes). My long-term research interest is studying learning systems from an information theoretic point of view contrary to the classic statistical inference framework (e.g. MLE, Bayesian inference). More broadly, I am interested in all aspects of probabilistic approaches to modelling and inference in machine learning.

I completed my PhD in the Machine Learning Group at the University of Cambridge, under the supervision of Zoubin Ghahramani. I was previously supervised by Chris Williams in the Informatics School at Edinburgh University.

Research papers

The Turing language

The Turing Team