High-Dimensional Asymptotics of Estimation Under Privacy and Computational Constraints — NSF Award to University of Wisconsin-Madi
Modern applications of AI and machine learning in fields such as genomics, neuroscience, healthcare, and social sciences depend on the analysis of vast high-dimensional datasets that often include highly sensitive personal information. As AI systems rely more on data, achieving high predictive accuracy is no longer eno
| Award title | High-Dimensional Asymptotics of Estimation Under Privacy and Computational Constraints |
|---|---|
| Award ID | 2610474 |
| Awardee | University of Wisconsin-Madison |
| City | MADISON |
| State | WI |
| Amount obligated | $179,999 |
| Principal investigator | Rishabh Dudeja |
| Program | STATISTICS |
| Start date | 07/01/2026 |
| Abstract | Modern applications of AI and machine learning in fields such as genomics, neuroscience, healthcare, and social sciences depend on the analysis of vast high-dimensional datasets that often include highly sensitive personal information. As AI systems rely more on data, achieving high predictive accuracy is no longer enough. Machine learning algorithms must also ensure privacy and remain computationally efficient at scale. This project investigates the fundamental trade-offs between accuracy, priv |
| Source | NSF Awards |
$799/mo
Try NSFGrants →