I am a PhD student at Stanford University advised by Percy Liang and Tengyu Ma. My main research interest is in machine learning with domain shifts – can we build machine learning models that perform well even when the train and test distribution are different, or at least signal low confidence when they are not able to make accurate predictions.
If you’re a Stanford student interested in working on a project on domain shifts / adaptation, or more broadly in safe and reliable machine learning, get in touch!
I’m lucky to have had the chance to work with many wonderful collaborators and advisors: Csaba Szepesvari, Jonathan Uesato, and Pushmeet Kohli on evaluating how safe RL agents are, Avrim Blum and Lin Yang on streaming algorithms for finding convex hulls, Guy Blelloch and Bob Harper on parallel functional arrays, and Ali Eslami, Danilo Rezende, and Murray Shanahan on generative models for videos and 3D scenes.
See my resume for more details on my professional experience. I also use Github and Linkedin.
