The National Science Foundation Division of Mathematical Sciences awarded Michigan State University $249,652 under the Mathematical and Physical Sciences (CFDA 47.049) federal grant program to support collaborative research towards designing optimal learning procedures via precise medium-dimensional asymptotic analysis. The three-year project grant aims to develop a novel analytical framework to quantitatively characterize the performance of diverse machine learning algorithms and provide guidance on designing optimal learning procedures. The research is expected to establish precise performance limits for a broad class of statistical learning methods and evaluate gaps between information-theoretic lower bounds and existing algorithm performance. Outcomes will provide insights to help solve various learning problems optimally across a range of statistical models in data-intensive environments. The award reflects the NSF's mission to advance mathematical and physical sciences and strengthen the national scientific enterprise.
Generated 1/6/24, 10:15 AM