I am a senior research scientist at Google DeepMind, working on building reliable deep learning models. My research interests lie in identifying precise mathematical definitions of similarity / diversity to understand the behavior of ML models. Most recently, I have been interested in the relationship between the diversity of a model predictions, and the model’s uncertainty about its predictions. I received my PhD from MIT, working with Suvrit Sra and as a member of the Machine Learning and Learning and Intelligent Systems groups. My PhD work focused on deriving and sampling from negatively dependent measures, which use Strongly Rayleigh polynomials to encode desirable properties in distributions over subsets of diverse items.