Philippe Rigollet awarded NSF BIGDATA grant

The National Science Foundation (NSF) has awarded LIDS faculty member and Professor of Mathematics, Philippe Rigollet, along with his co-principal investigators for his research titled “Statistical and Computational Optimal Transport for Geometric Data Analysis”. The NSF BIGDATA program is a major initiative that aims to advance the core scientific and technological means of managing, analyzing, visualizing, and extracting useful information from large and complex data sets.

“The theory of optimal transport has proven valuable to address data that is not a collection of individual points, but rather whole geometric objects,” says Rigollet. “Yet, understanding optimal transport as a statistical tool is still in its infancy.” The nascent theory of computational optimal transport is still largely dissociated from statistics, and many methods do not account properly for sampling and measurement noise. To avoid the pitfalls of overfitting, Rigollet and Solomon propose to take a systematic statistical approach to geometric data analysis. With an understanding of theoretical advantages and drawbacks of optimal transport for statistical modeling, this project will lead to scalable optimal transport algorithms with strong statistical guarantees.

Photos credited to Bryce Vickmark. For more information, please see this link.