Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm

Abstract: 

Extracting inherent patterns from large data using decompositions of
data matrix by a sampled subset of exemplars has found many applications
in machine learning. We propose a computationally efficient
algorithm for adaptive exemplar sampling, called fast exemplar selection
(FES). The proposed algorithm can be seen as an efficient
variant of the oASIS algorithm (Patel et al). FES iteratively selects incoherent
exemplars based on the exemplars that are already sampled.
This is done by ensuring that the selected exemplars forms a positive
definite Gram matrix which is checked by exploiting its Cholesky
factorization in an incremental manner. FES is a deterministic rank
revealing algorithm delivering a tighter matrix approximation bound.
Further, FES can also be used to exactly represent low rank matrices
and signals sampled from a unions of independent subspaces. Experimental
results show that FES performs comparable to existing
methods for tasks such as matrix approximation, feature selection,
outlier detection, and clustering.

up
0 users have voted:

Paper Details

Authors:
Pulkit Sharma, Anil Kumar Sao
Submitted On:
28 February 2017 - 12:26am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Vinayak Abrol
Paper Code:
3376
Document Year:
2017
Cite

Document Files

conference_poster_4.pdf

(102 downloads)

Subscribe

[1] Pulkit Sharma, Anil Kumar Sao, "Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1474. Accessed: Sep. 20, 2017.
@article{1474-17,
url = {http://sigport.org/1474},
author = {Pulkit Sharma; Anil Kumar Sao },
publisher = {IEEE SigPort},
title = {Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm},
year = {2017} }
TY - EJOUR
T1 - Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm
AU - Pulkit Sharma; Anil Kumar Sao
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1474
ER -
Pulkit Sharma, Anil Kumar Sao. (2017). Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm. IEEE SigPort. http://sigport.org/1474
Pulkit Sharma, Anil Kumar Sao, 2017. Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm. Available at: http://sigport.org/1474.
Pulkit Sharma, Anil Kumar Sao. (2017). "Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm." Web.
1. Pulkit Sharma, Anil Kumar Sao. Fast Exemplar Selection Algorithm for Matrix Approximation and Representation: A Variant oASIS Algorithm [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1474