Contact: gen.disc.nips09 at

SLJ.jpg Simon Lacoste-Julien (University of Cambridge) is a postdoctoral researcher in the Machine Learning Group at the University of Cambridge. He has worked on exploiting different types of structure for discriminative learning methods: structure on outputs, such as the combinatorial structure in word alignment; structure on inputs, such as in latent variable models used in text document classification. Recently, he has been working on the combination of generative and discriminative methods.
percy.jpg Percy Liang (UC Berkeley) is a graduate student at UC Berkeley. His research spans a wide range of topics, including building nonparametric Bayesian models of natural language, developing efficient methods for training complex graphical models, and creating a framework for learning that unifies labeled examples with general constraints. He has also used asymptotic statistics to reveal new insights about generative versus discriminative learning (winning a best student paper award at ICML 2008), and more recently, to analyze regularization.
GuillaumeBouchard.jpg Guillaume Bouchard (Xerox Research Centre Europe) is a researcher in the Machine Learning and optimization for Services group at Xerox Research Centre Europe. He works on approximate Bayesian inference algorithms and their applications. He developed techniques that smoothly interpolate between the generative and discriminative estimation. He is interested in developing probabilistic methods in which expert knowledge can be easily introduced.
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License