I am a assistant professor in the department of decision sciences at HEC (and adjunct at the DIRO). I develop novel machine learning models, particularly probabilistic graphical models, to help in decision making. My recent work has focused on extending the capabilities of recommender systems.
I am generally interested in applying learning methods to analyze different data.
I have co-developed the Toronto Paper Matching System (TPMS) which is a tool to assist conference organizers match their reviewers to submitted papers. The system is now online and has been used by large machine learning and computer vision conferences over the last few years.
I graduated with a PhD from the University of Toronto where I worked with Rich Zemel and Craig Boutilier. I also have a Master’s from U. Waterloo where I was supervised by Pascal Poupart. Finally, I did postdocs at Princeton and Columbia under the supervision of David Blei and at McGill with Joelle Pineau.