Abhishek Shetty

I am the incoming Catherine M. and James E. Allchin Early-Career Assistant Professor in Computer Science at Georgia Tech, starting in Fall 2026. Currently, I am a FODSI postdoctoral fellow at Massachussets Institute of Technology hosted by Costis Daskalakis, Ankur Moitra and Sasha Rakhlin. Previous, I was a PhD student at the University of California at Berkeley under the wise guidance of Nika Haghtalab.

I am also fortunate to have worked with Lester Mackey at MSR New England during the summer of 2021, Akshay Krishnamurthy and Cyril Zhang at MSR NYC during the summer of 2022 and Parikshit Gopalan at Apple during the summer of 2023. I am honored to be amongst the 2023 cohort of the Apple AI/ML fellowship.

My research has been focussed on exploring the intersection of theoretical computer science and modern machine learning. I see my long term research goal as understanding minimal structures that allow reasoning about complex systems through limited access (be it computation or information). Recently, this has manifested through

• Understanding the foundational and algorithmic landscape of modern machine learning, in particular, large language models
• Foundations of statistical inference and decision-making, especially under limited independence
• Methods for data compression especially ones inspired by discrepancy theory

You can find a link to my CV here.

I am looking to recruit motivated students and postdocs interested in the intersection of theoretical computer science and modern machine learning at Georgia Tech.