Current interests:

• Fairness in machine learning.
• Unsupervised learning
• Algorithms and Systems for Big Data and Machine Learning.

Other interests: Coding theory, Erasure coding for distributed storage, Computational Complexity.
I am currently interested in algorithms and systems for big data and machine learning.

• Hillview is an interactive visualization engine for large distributed data sets that be used to explore tables with a trillion cells, and that exclusively runs on sketching and streaming algorithms.
• My work in Machine Learning focuses on rigorous and scalable methods for Anomaly Detection.

In the past, I have been a researcher at Microsoft Research (Silicon Valley and Redmond), a postdoc at UT Austin and the University of Washington, a Ph. D student at Georgia Tech, and an undergraduate at IIT Bombay. I have worked on coding theory, erasure coding for distributed storage and computational complexity.