I am a research scientist at Google. My current focus is designing and analyzing optimization methods for federated learning. I actively contribute to TensorFlow Federated, Google’s open-source framework for federated learning experimentation, and Federated Research, Google’s open-source repository for federated learning research.

I received a Ph.D. in applied mathematics from the University of Wisconsin-Madison, and went on to do a postdoc with the wonderful Dimitris Papailiopoulos. In my limited free time I often foster dogs and bake. You can find recipes I am fond of in my dissertation (no, really).


I am generally interested in optimization for machine learning, especially federated learning. I tend to focus on developing holistic understandings of algorithms that incorporate communication-efficiency, robustness, fairness, and practicality. I am particularly interested in reconciling optimization theory with practical machine learning. Much of my work does this by leveraging tools from probability theory and high-dimensional statistics.

Publications & Preprints





2017 and earlier