Article

 

ESTIMATING ACTIVE SUBSPACES WITH RANDOMIZED GRADIENT SAMPLING Público Deposited

Analytics

Contenido Descargable

Descargar PDF
Citations
https://scholar.colorado.edu/concern/articles/td96k311g
Abstract
  • In this work, we present an efficient method for estimating active subspaces using only random observations of gradient vectors. Our method is based on the bi-linear representation of low-rank gradient matrices with a novel initialization step for alternating minimization.
Creator
Date Issued
  • 2017-07-01
Academic Affiliation
Journal Title
Última modificación
  • 2019-12-05
Resource Type
Declaración de derechos
Language

Relaciones

Elementos

Miniatura Título Fecha de subida Visibilidad Acciones
Pg15bf59j?file=thumbnail estimatingActiveSubspacesWithRandomizedGradientSampling.pdf 2019-12-05 Público Descargar