Hunting for Low-Dimensional in High Dimensional Data

Abstract

Big data is typically high dimensional, while information that is useful to humansis low dimensional. The PI will explore mathematically and algorithmically methods for extracting meaningful information/data from massive distributed data. Key areas of investigation include: finding the most structured low-dimensional projections of high-dimensional data AND determining how to identify low-dimensional "effective domains".

Document Details

Document Type
DoD Grant Award
Publication Date
Apr 09, 2018
Source ID
FA95501810031

Entities

People

  • Roman Vershynin

Organizations

  • Air Force Office of Scientific Research
  • United States Air Force
  • University of California, Irvine

Tags

Readers

  • Neural Network Machine Learning.