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 title | CAREER: An Architecture-Aware Optimization Theory for Deep Learning: Non-Euclidean Descent |
|---|---|
| Award ID | 2544658 |
| Awardee | Toyota Technological Institute at Chicago |
| City | CHICAGO |
| State | IL |
| Amount obligated | $349,963 |
| Principal investigator | Zhiyuan Li |
| Program | Robust Intelligence |
| Start date | 06/01/2026 |
| Abstract | 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 different model architectures. This project will develop a scientific foundation for making training faster, more reliable, and more resource efficient by linking optimization methods |
| Source | NSF Awards |
$799/mo
Try NSFGrants →