← NSFGrants
HomeNsf Awards

CAREER: An Architecture-Aware Optimization Theory for Deep Learning: Non-Euclidean Descent — NSF Award to Toyota Technological Ins

Training modern artificial intelligence systems requires large amounts of computing time, energy, and money. Many of the optimization methods used to train neural networks are still chosen largely through trial and error because existing theory does not adequately explain why some methods work better than others on dif

Award titleCAREER: An Architecture-Aware Optimization Theory for Deep Learning: Non-Euclidean Descent
Award ID2544658
AwardeeToyota Technological Institute at Chicago
CityCHICAGO
StateIL
Amount obligated$349,963
Principal investigatorZhiyuan Li
ProgramRobust Intelligence
Start date06/01/2026
AbstractTraining modern artificial intelligence systems requires large amounts of computing time, energy, and money. Many of the optimization methods used to train neural networks are still chosen largely through trial and error because existing theory does not adequately explain why some methods work better than others on different model architectures. This project will develop a scientific foundation for making training faster, more reliable, and more resource efficient by linking optimization methods
SourceNSF Awards

🔍 Search all NSF awards →