The USA’s National Academy of Sciences elected 84 new members and 21 foreign associates from 15 countries this year, in recognition of their distinguished and continuing achievements in original research. Among them was IMS Fellow Donald Geman, who is Professor in the Department of Applied Mathematics and Statistics at Johns Hopkins University, Baltimore, MD, and simultaneously a visiting professor at École Normale Supérieure de Cachan.

Donald Geman was born in Chicago in 1943. He graduated from the University of Illinois at Urbana-Champaign in 1965 with a BA in English Literature and from Northwestern University in 1970 with a PhD in Mathematics. He worked as a Professor in the Department of Mathematics and Statistics at the University of Massachusetts following graduation, until he joined Johns Hopkins University in 2001.

Donald was elected a Fellow of IMS in 1997, and of the Society for Industrial and Applied Mathematics (SIAM) in 2010. He gave an IMS Medallion Lecture in 2012 at JSM San Diego, on “Order Statistics and Gene Regulation.”

Donald Geman, The Johns Hopkins University
Donald Geman (right) gave an IMS Medallion Lecture in 2012 at JSM in San Diego. He is pictured here with Peter Bickel, who chaired the session.

Donald Geman and Joseph Horowitz published a series of papers during the late 1970s on local times and occupation densities of stochastic processes. In 1984, with his brother Stuart, he published a milestone paper which is still today one of the most cited papers in the engineering literature—according to Google Scholar the paper has over 16,900 citations. It introduces a Bayesian paradigm using Markov Random Fields for the analysis of images, and the Gibbs sampler algorithm. This approach has been highly influential over the last 30 years and remains a rare tour de force in this rapidly evolving field. In another milestone paper, in collaboration with Yali Amit, he introduced randomized decision trees—what Leo Breiman called random forests.

Donald lists his current research areas as Computational Vision (scene interpretation by “entropy pursuit” and Turing tests for vision systems) and Computational Molecular Medicine (rank discriminants for predicting cancer phenotypes, hardwiring biological mechanisms into statistical learning, and modeling tumorigenesis). Read more on his website: