MAGE Faculty

EDUCATION

• Ph.D., Electrical and Computer Engineering, Carnegie Mellon University
• M.S., Electrical and Computer Engineering, Carnegie Mellon University
• B. Tech., Electronics and Electrical Communication Engineering, Indian Institute of Technology, Kharagpur

AWARDS

• 2024 NSF CAREER Award
• 2024 George Corcoran Memorial Award
• 2023 JPMorgan Faculty Award
• 2023 Northrop Grumman Seed Grant
• 2022 Simons Institute Fellowship for Causality
• 2021 A G Milnes Outstanding Thesis Award
• 2020 Cylab Presidential Fellowship
• 2019 K&L Gates Presidential Fellowship in Ethics and Computational Technologies
• 2019 Axel Berny Presidential Graduate Fellowship
• 2017 Tan Endowed Graduate Fellowship
• 2016 Prabhu and Poonam Goel Graduate Fellowship
• 2015 Nilanjan Ganguly Memorial Award for Best B. Tech. Thesis
• 2014 HONDA Young Engineer and Scientist Award

ABOUT

Sanghamitra Dutta is an assistant professor in the Department of Electrical and Computer Engineering at the University of Maryland College Park since Fall 2022. She is also affiliated with the Center for Machine Learning (CML) at UMIACS, the Department of Computer Science, the Values-Centered Artificial Intelligence (VCAI), the Applied Mathematics & Statistics, and Scientific Computation (AMSC), and the Artificial Intelligence Interdisciplinary Institute at Maryland (AIM). Prior to joining UMD, she was a senior research associate at JPMorgan Chase AI Research New York in the Explainable AI Centre of Excellence (XAI CoE). She received her Ph.D. and Master's from Carnegie Mellon University and B. Tech. from IIT Kharagpur, all in Electrical and Computer Engineering. 

Her research interests broadly revolve around reliable, efficient, and trustworthy machine learning. She is particularly interested in addressing the challenges concerning explainability, efficiency, privacy, and reliability, by bringing in a novel foundational perspective deep-rooted in information theory, statistics, causality, and optimization. Her research has featured in New Scientist and Montreal AI Ethics Brief, and also been adopted as part of the fair-lending model review at JPMorgan.

In her prior work, she has also examined problems in reliable computing, proposing novel algorithmic solutions for large-scale distributed machine learning, using tools from coding theory (an emerging area called “coded computing”). Her results on coded computing has received substantial attention from across disciplines.

She is a recipient of the 2024 NSF CAREER Award, 2024 George Corcoran Memorial Award, 2023 JPMorgan Faculty Award, 2023 Northrop Grumman Seed Grant, 2022 Simons Institute Fellowship for Causality, 2021 AG Milnes Outstanding Thesis Award from CMU and 2019 K&L Gates Presidential Fellowship in Ethics and Computational Technologies. She has also pursued research internships at IBM Research and Dataminr. 

Her research vision is to build the foundations of reliable, efficient, and trustworthy artificial intelligence (AI), beginning from a fundamental understanding of the challenges in explainability, reliability, fairness,  and privacy, and carrying them all the way to practical implementations, so that AI can truly bring about social good.

Her research interests include:

• Trustworthy Machine Learning
• Efficiency
• Explainability
• Fairness and Privacy
• Information Theory 
• Optimization, Statistics, Estimation Theory
• Causal Inference
• Coded Computing

ENEE621: Detection and Estimation Theory     Spring 2023, Spring 2025

ENEE436: Foundations of Machine Learning     Fall 2022, Fall 2023, Fall 2024

2025

• F. Hamman, P. Dissanayake, S. Mishra, F. Lecue, S. Dutta, "Quantifying Prediction Stability Under Fine-tuning Multiplicity in Tabular LLMs" International Conference on Machine Learning (ICML 2025).  
• P. Dissanayake, F. Hamman, B. Halder, Q. Zhang, I. Sucholutsky, S. Dutta, "Quantifying Knowledge Distillation using Partial Information Decomposition" Artificial Intelligence and Statistics (AISTATS 2025).

• E. Noorani, P. Dissanayake, F. Hamman, S. Dutta, "Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures," International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025).

2024

• P. Dissanayake and S. Dutta, "Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory," Advances in Neural Information Processing Systems (NeurIPS 2024).
• F. Hamman and S. Dutta, "Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition," International Conference on Learning Representations (ICLR 2024).
• F. Hamman and S. Dutta, "A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition," IEEE International Symposium on Information Theory (ISIT 2024).
• A. K. Veldanda, I. Brugere, S. Dutta, A. Mishler, and S. Garg. "Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access," Transactions on Machine Learning Research (TMLR 2024).
• F. Hamman, E. Noorani, S. Mishra, D. Magazzeni, and S. Dutta, "Robust Algorithmic Recourse Under Model Multiplicity with Probabilistic Guarantees," IEEE Journal on Selected Areas in Information Theory: Information-Theoretic Methods for Trustworthy Machine Learning (JSAIT 2024).
• B. Halder, F. Hamman, P. Dissanayake, Q. Zhang, I. Sucholutsky, and S. Dutta, "Quantifying Spuriousness of Biased Datasets Using Partial Information Decomposition" ICML Workshop on Data-centric Machine Learning Research: Datasets for Foundation Models (ICML-DMLR Workshop 2024).
• P. Dissanayake, F. Hamman, B. Halder, I. Sucholutsky, Q. Zhang, and S. Dutta. “Formalizing Limits of Knowledge Distillation Using Partial Information Decomposition”. In: NeurIPS Workshop on Machine Learning and Compression (2024).

2023

• F. Hamman, E. Noorani, S. Mishra, D. Magazzeni, and S. Dutta, "Robust Counterfactual Explanations for Neural Networks with Probabilistic Guarantees," International Conference on Machine Learning (ICML 2023).
• F. Hamman and S. Dutta, "Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition," ICML Workshop on Federated Learning and Analytics in Practice (ICML-FL Workshop 2023).
• S. Sharma, S. Dutta, E. Albini, F. Lecue, D. Magazzeni and M. Veloso, "REFRESH: Responsible and Efficient Feature Reselection guided by SHAP values," AAAI/ACM Conference on AI, Ethics, and Society (AIES 2023).
• F. Hamman, J. Chen, and S. Dutta, "Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity," ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2023). 
• S. Garg, S. Dutta, M. Dalirrooyfard, A. Schneider, Y. Nevmyvaka, "In- or Out-of-Distribution Detection via Dual Divergence Estimation," Conference on Uncertainty in Artificial Intelligence (UAI 2023). 
• A. K. Veldanda, I. Brugere, J. Chen, S. Dutta, A. Mishler, and S. Garg, "Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale," Transactions on Machine Learning Research (TMLR 2023).

• S. Dutta, F. Hamman, "A Review of Partial Information Decomposition in Algorithmic Fairness and Explainability," Entropy 2023.

2022

• S. Dutta, J Long, S Mishra, C Tilli, D Magazzeni, "Robust Counterfactual Explanations for Tree-Based Ensembles," International Conference on Machine Learning (ICML 2022). 
• P. Mathur, A T Neerkaje, M Chhibber, R Sawhney, F Guo, F Dernoncourt, S Dutta, D Manocha, "MONOPOLY: Financial Prediction from MONetary POLicY Conference Videos Using Multimodal Cues," ACM Multimedia 2022 (ACM-MM 2022).
• F. Hamman, J. Chen, and S. Dutta, "Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity," NeurIPS Workshop on Algorithmic Fairness through the Lens of Causality and Privacy (NeurIPS-AFCP Workshop 2022).
• S Dutta, P Venkatesh, P Grover, "Quantifying Feature Contributions to Overall Disparity Using Information Theory," AAAI-22 Workshop on Information-Theoretic Methods for Causal Inference and Discovery (AAAI Workshop 2022).

2021

• P Venkatesh, S Dutta*, N Mehta*, P Grover, "Can Information Flows Suggest Targets for Interventions in Neural Circuits?," Advances in Neural Information Processing Systems (NeurIPS 2021).
• S. Dutta, P. Venkatesh, P. Mardziel, A. Datta and P. Grover, "Fairness under Feature Exemptions: Counterfactual and Observational Measures," IEEE Transactions on Information Theory 2021. 
• S. Dutta, J. Wang, and G. Joshi, "Slow and stale gradients can win the race," IEEE Journal on Selected Areas in Information Theory 2021.
• S Mishra, S Dutta, J Long, D Magazzeni, "A Survey on the Robustness of Feature Importance and Counterfactual Explanations," Explainable AI in Finance (XAI-FIN21). 
• C. Jiang*, B. Wu*, S. Dutta and P. Grover, "Bursting the Bubbles: Debiasing Recommendation Systems While Allowing for Chosen Category Exemptions," BIAS Workshop at ECIR (ECIR Workshop 2021).
• S. Dutta, L. Ma, T. K. Saha, D. Liu, J. Tetreault, and A. Jaimes, "GTN-ED: Event Detection Using Graph Transformer Networks," TextGraphs Workshop at NAACL (NAACL Workshop 2021).

2020

• S. Dutta, D. Wei, H. Yueksel, P. Y. Chen, S. Liu, and K. R. Varshney, "Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing," International Conference on Machine Learning (ICML 2020). 
• S. Dutta, P. Venkatesh, P. Mardziel, A. Datta and P. Grover, "An Information-Theoretic Quantification of Discrimination with Exempt Features," AAAI Conference on Artificial Intelligence (AAAI 2020, ORAL). 
• P. Venkatesh, S. Dutta, and P. Grover, "How else should we define Information Flow in Neural Circuits,” IEEE International Symposium on Information Theory (ISIT 2020).
• P. Venkatesh, S. Dutta, and P. Grover, "Information Flow in Computational Systems,” IEEE Transactions on Information Theory, Sep 2020.
• S. Dutta*, M. Fahim*, H. Jeong*, F. Haddadpour*, V. Cadambe, and P. Grover, "On the Optimal Recovery Threshold of Coded Matrix Multiplication," IEEE Transactions on Information Theory, Jan 2020.
• S. Dutta*, H. Jeong*, Y. Yang*, V. Cadambe, T. M. Low and P. Grover, “Addressing Unreliability in Emerging Devices and Non-von Neumann Architectures Using Coded Computing," Proceedings of the IEEE, April 2020.

2019

• P. Venkatesh, S. Dutta and P. Grover, "How should we define Information Flow in Neural Circuits,” IEEE International Symposium on Information Theory (ISIT 2019).
• S. Dutta, V. Cadambe and P. Grover, "Short-Dot: Computing Large Linear Transforms Distributedly using Coded Short Dot Products," IEEE Transactions on Information Theory, Oct 2019.
• S. Dutta, Z. Bai, T. M. Low and P. Grover, "CodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors," Coding Theory For Large-scale Machine Learning Workshop at ICML (CodML Workshop, ICML 2019, Spotlight).

2018

• S. Dutta, G. Joshi, P. Dube, S. Ghosh, and P. Nagpurkar, "Slow and stale gradients can win the race: Error-Runtime trade-offs in Distributed SGD," International Conference on Artificial Intelligence and Statistics (AISTATS 2018).
• U. Sheth, S. Dutta, M. Chaudhari, H. Jeong, Y. Yang, J. Kohonen, T. Roos, and P. Grover, "An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation,” IEEE International Conference on Big Data (IEEE BigData 2018).
• S. Dutta*, Z. Bai*, H. Jeong, T. M. Low, and P. Grover, "A Unified Coded Deep Neural Network Training Strategy based on Generalized PolyDot Codes," IEEE International Symposium on Information Theory (ISIT 2018).

2017

• S. Dutta, V. Cadambe and P. Grover, "Coded Convolution for parallel and distributed computing within a deadline," IEEE International Symposium on Information Theory (ISIT 2017).
• M. Fahim*, H. Jeong*, F. Haddadpour, S. Dutta, V. Cadambe, and P. Grover, "On the Optimal Recovery Threshold of Coded Matrix Multiplication," Communication, Control and Computing (Allerton 2017).

2016

• S. Dutta, V. Cadambe and P. Grover, "Short-Dot: Computing Large Linear Transforms Distributedly using Coded Short Dot Products," Advances in Neural Information Processing Systems (NeurIPS 2016).
• S. Dutta and P. Grover, "Adaptivity provably helps: Information-theoretic limits on l0 cost of non-adaptive sensing," IEEE International Symposium on Information Theory (ISIT 2016).
• S. Dutta, Y. Yang, N. Wang, E. Pop, V. Cadambe and P. Grover, “Reliable Matrix Multiplication using Error-prone Dot-product Nanofunctions with an application to logistic regression” (SRC Techcon, 2016).

2015

• S. Dutta and A. De, "Sparse UltraWideBand Radar Imaging in a Locally Adapting Matching Pursuit (LAMP) Framework," IEEE International Radar Conference (RADAR 2015).