My research area is machine learning.
I’m broadly interested in the problem of representation learning and inference in structured, complex and combinatorial domains.
In addition to its potential role in artificial general intelligence, our ability to draw inference with structured data is essential in a data-driven approach to science. My recent works explore symmetry transformations in deep learning. This is succinctly motivated by Hermann Weyl’s guiding principle:
Whenever you have to do with a structure-endowed entity, try to determine [...] those transformations which leave all structural relations undisturbed.
COMP 551: Applied Machine Learning (Fall 2021)
COMP 766-002: Probabilistic Graphical Models (Winter 2021)
COMP 551: Applied Machine Learning (Fall 2020)
COMP 551: Applied Machine Learning (Winter 2020)
COMP 767-002: Probabilistic Graphical Models (Fall 2019)
CPSC 532R (at UBC) : Advanced Topics in AI: Graphical Models (Winter 2018)
Before joining McGill and Mila, I held a similar position at the University of British Columbia. Before that, I was a postdoctoral fellow at the Machine Learning Department and the Robotics Institute, at the Carnegie Mellon University. There, I worked with Barnabás Póczos and Jeff Schneider, and I was also affiliated with Auton Lab and McWilliams Center for Cosmology. I received my M.Sc. and Ph.D. from the University of Alberta, as a member of Alberta Ingenuity Center for Machine Learning, now amii, working with Russ Greiner. During this time, I also spent a few months at Frey Lab, at the University of Toronto. Prior to that, I received my B.Sc. from Sharif University.