Published multiple papers including 'Self-improvement in language models: The sharpening mechanism', 'Transformers learn shortcuts to automata', 'Efficient first order contextual bandits: Prediction, allocation, and triangular discrimination', and more, with several oral presentations at international conferences.
Research Experience
Currently a Senior Principal Research Manager at Microsoft Research, New York City. Previously, an assistant professor at the College of Information and Computer Sciences at the University of Massachusetts, Amherst for two years, and a postdoctoral researcher at Microsoft Research, NYC for one year.
Education
PhD: Computer Science Department at Carnegie Mellon University, advised by Aarti Singh; Undergraduate: EECS at UC Berkeley.
Background
Research interests: machine learning and statistics, with a focus on interactive learning, decision making (including contextual bandits and reinforcement learning), and how these frameworks manifest in language modeling and generative AI.