Shana Moothedath receives NSF CAREER Award to develop efficient, safe multi-task learning algorithms
Author: Lani McKinney
Shana Moothedath, assistant professor of electrical and computer engineering, has received a National Science Foundation (NSF) CAREER Award for research to develop provable methods for multi-task representation learning in bandit and reinforcement learning settings.
The CAREER Award is the NSF’s most prestigious honor to support junior faculty.
Moothedath’s CAREER project is “CAREER: A Principled Framework for Multi-Task Representation Learning for Scalable, Decentralized, and Safe Sequential Decision-Making.” The award’s total value is $515,000 beginning Sept. 1, 2025 for an estimated five-year period.
About the research project
Moothedath’s research develops multi-task learning algorithms that leverage problem structures to enable efficient, privacy-preserving learning in dynamic systems while addressing data heterogeneity, communication efficiency, scalability, and safety constraints.
As part of her CAREER project, Moothedath intends to boost engagement in STEM education with an integrated education plan providing a pathway for K-12 to college students to receive rigorous math training and hands-on experience, including coding skills for machine learning-based intelligent system design.
The project is funded by NSF’s Division of Electrical, Communications and Cyber Systems.
About Shana Moothedath
Moothedath holds a Ph.D. from the Indian Institute of Technology Bombay. Her research interests include distributed/federated learning; reinforcement learning; bandit learning; control and security of cyber-physical systems; analysis and control of networked systems; and control and optimization.