H O M E

About me: I am a Killam postdoctoral fellow in machine learning working with Kevin Murphy in the department of computer science at the University of British Columbia. I completed my PhD in machine learning in the department of computer science at the University of Toronto in 2008 working under Rich Zemel. I completed my master's degree in machine learning, also under Rich Zemel, in 2004. I received my undergraduate degree from McGill University in mathematics and computer science in 2002.

Upcoming Papers:

[Sept 8, 2009] Baback Moghaddam, Benjamin M. Marlin, Emtiyaz Khan, Kevin Murphy. Accelerating Bayesian Structural Inference for Non-Decomposable Gaussian Graphical Models. To appear at the Neural Information Processing Systems Conference (NIPS) December 7-10 2009.

Recent Papers:

[Oct 26, 2009] Benjamin M. Marlin and Richard Zemel. Collaborative Prediction and Ranking with Non-Random Missing Data. Proceedings of the 3rd ACM Conference on Recommender Systems. 2009. Winner of best technical paper award. [Paper PDF] [Slides PDF].
[June 20, 2009] Benjamin M. Marlin, Mark Schmidt and Kevin P. Murphy. Group Sparse Priors for Covariance Estimation. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. 2009. [Paper PDF] [Poster PDF]

[June 16, 2009] Benjamin M. Marlin and Kevin P. Murphy. Sparse Gaussian Graphical Models with Unknown Block Structure. Proceedings of the 26th International Conference on Machine Learning. 2009. [Paper PDF] [Slides PDF] [Poster PDF]

PhD Thesis: My PhD thesis is titled Missing Data Problems in Machine Learning. It deals with the problem of unsupervised learning in the presence of non-random missing data, as well as the problem of classification in the presence of missing features. The work on non-random missing data is motivated by the problem of rating prediction in collaborative filtering, and uses a new data set collected at Yahoo! Research with Malcolm Slaney. The work on classification with missing features focuses on medical decision making using standard data sets, as well as higher dimensional tasks like digit classification with missing pixels. [Thesis Abstract] [Thesis PDF] [Short Defense Slides PDF] [Long Defense Slides PDF]

Reading Groups: I maintain the website for the Machine Learning and Computational Neuroscience reading groups at UBC.

Email: bmarlin[at]cs[dot]ubc[dot]ca