Sanghamitra Dutta

Assistant Professor, University of Maryland College Park

About Myself:

My research interests broadly revolve around reliable and trustworthy machine learning. I am particularly interested in addressing the challenges concerning fairness, explainability, and reliability, by bringing in a novel foundational perspective, deep-rooted in information theory and causality.

Prior to joining UMD, I was a senior research associate at JPMorgan Chase AI Research in the Explainable AI Centre of Excellence (XAI CoE). My research on algorithmic fairness has been adopted as part of the fair lending model review at JPMorgan.

I also received the Simons Institute Fellowship for Causality Program in 2022.

I received my Ph. D. from Carnegie Mellon University. My thesis proposes a systematic quantification of the legally non-exempt disparity in machine learning models, bringing together causality, information theory, and law. I have received the 2019 K&L Gates Presidential Fellowship in Ethics and Computational Technologies for my research in this direction. My research on quantifying accuracy-fairness tradeoffs using information theory (with IBM Research) was featured in New Scientist. My Ph.D. thesis received the 2021 A G Milnes Outstanding Thesis Award.

In my prior work, I have examined problems in reliable computing, proposing solutions for large-scale distributed machine learning using tools from coding theory (an emerging area called “coded computing”). My results on coded computing address problems in algorithm-based-fault-tolerance that have been open for several decades and have received substantial attention from across disciplines.

I am currently looking for motivated students to join my research group!

Prospective Students: Please apply to the UMD Graduate Program and mention my name in your Statement of Purpose.

Current Students: If you are already admitted to UMD, please send me an email with your resume and transcript.


  • Fairness, Explainability, Policy, Law

  • Information Theory, Coding Theory

  • Statistics, Optimization

  • Causality

  • Natural Language Processing

  • Distributed Machine Learning

  • Performance Modeling and Queueing

  • Compressive Sensing and Sparse Linear Algebra