I am a 4th year PhD student at Brown University, working on Reinforcement Learning, advised by Professor George Konidaris.

Prior to this I obtained a masters degree from University of Massachusetts, Amherst and had the privilege of working with Professor Phil Thomas. I graduated with a Bachelors of Technology in computer science at IIT Bombay in 2014. My research is focused on designing a geometric lense for understanding Deep Reinforcement Learning. High dimensional data has a low dimensional structure to it. For example, a picture of a face might have 2^16 pixels but we can describe a face with far fewer variables: size of the nose, color of the skin, shape of the eyes etc. This forms the manifold hypothesis: high-dimensional data lies on (or close to) a low-dimensional manifold. Armed with this we try to answer two questions:

1. How do existing deep learning models utilise this low-dimensional structure?
2. How can we exploit this low-dimensional structure to train better models?

My approach is theory-in-practice. Meaning I work with theoretical tools that can help explain the popular practical algorithms in use with as few assumptions as possible.