This Project Grant award of $948,000 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program will support research to develop new methods for data-efficient decision-focused learning. The research aims to create a general framework for tailoring predictive models to capture underlying uncertainty factors and integrate them into complex decision-making problems in domains such as public health, environmental sustainability, and urban planning. The award will fund the development of a modularized pre-training and fine-tuning approach to build flexible predictive models that can effectively solve stochastic decision-making problems with limited data, while addressing challenges like model misspecification and distribution shifts. The research will be conducted by the Georgia Tech Research Corporation at the Georgia Institute of Technology from September 2024 through August 2028.
Generated 3/4/25, 4:25 AM