This $267,816 Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences (CFDA 47.049) program will support research at the University of Massachusetts (UMass) to develop a unified framework for variational inference algorithms used in machine learning and artificial intelligence. The key products of this 2-year project include:
-
Establishing the theoretical foundations for an "energetic variational inference" framework to support the use of existing and new variational inference algorithms in machine learning applications.
-
Providing a systematic procedure to create new variational inference algorithms and apply them to emerging machine learning problems.
Additionally, the project will create new educational courses and training programs on machine learning for students at various levels, and collaborate with industry partners to apply the new algorithms in practice. UMass will also issue two sub-awards totaling an undisclosed amount to the IIT Research Institute and University of California, Riverside to contribute specialized expertise in this research effort.
Generated 2/25/25, 3:10 AM