← NSFGrants
HomeNsf Awards

Unsupervised Learning and Nonlinear Dimension Reduction: Advances with Optimal Transport, — NSF Award to Columbia University (NY,

Modern scientific data sets—ranging from single-cell RNA sequencing with tens of thousands of genes per patient, to galaxy-survey spectra with millions of stars, to user-item interaction matrices in online platforms—share two features: (i) ultra-high dimensionality and (ii) latent parameters that obey common structural

Award titleUnsupervised Learning and Nonlinear Dimension Reduction: Advances with Optimal Transport,
Award ID2515520
AwardeeColumbia University
CityNEW YORK
StateNY
Amount obligated$240,000
Principal investigatorBodhisattva Sen
ProgramSTATISTICS
Start date07/01/2025
AbstractModern scientific data sets—ranging from single-cell RNA sequencing with tens of thousands of genes per patient, to galaxy-survey spectra with millions of stars, to user-item interaction matrices in online platforms—share two features: (i) ultra-high dimensionality and (ii) latent parameters that obey common structural laws (e.g., exchangeability, sparsity, or low-rank dependence). This project tackles both challenges at once. It advances statistical foundations for such problems by (1) providin
SourceNSF Awards

🔍 Search all NSF awards →