Article

 

ESTIMATING ACTIVE SUBSPACES WITH RANDOMIZED GRADIENT SAMPLING Pubblico Deposited

Analytics

Contenuto scaricabile

Scarica il 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
Ultima modifica
  • 2019-12-05
Resource Type
Dichiarazione dei diritti
Language

Le relazioni

Elementi

Thumbnail Titolo Data caricata Visibilità Azioni
Pg15bf59j?file=thumbnail estimatingActiveSubspacesWithRandomizedGradientSampling.pdf 2019-12-05 Pubblico Scaricare