I work on problems related to large scale machine learning. My research focuses on robust machine learning, developing models and features that are robust to:

  • changes in the distribution of features and labels across train and test sets (transfer learning)
  • low sample size and extremely low signal to noise ratio regimes
  • extracting features from unstructured data

I am particularly interested in applications of robust machine learning to time series and natural language processing models.

After graduating from Columbia University with a BA in Computer Science and AI in 2003, I joined the original Google New York office in early 2004 where I worked on an early version of Google Maps. My passion for AI and machine learning prompted me to return to school to pursue my Ph.D. in Machine Learning from Carnegie Mellon University, graduating in 2009. I spent the next nine years working as a portfolio manager using machine learning to develop quantitative trading strategies. I rejoined Google NYC in 2018.

To learn more please visit