TY - GEN
T1 - Online kernel dictionary learning on a budget
AU - Lee, Jeon
AU - Kim, Seung Jun
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/3/1
Y1 - 2017/3/1
N2 - Online kernel-based dictionary learning (DL) algorithms are considered, which perform DL on training data lifted to a high-dimensional feature space via a nonlinear mapping. Compared to batch versions, online algorithms require low computational complexity, essential for processing the Big Data, based on the stochastic gradient descent method. However, as with any kernel-based learning algorithms, the number of parameters needed to represent the desired dictionary is equal to the number of training samples, which incurs prohibitive memory requirement and computational complexity for large-scale datasets. In this work, appropriate sparsification and pruning strategies are combined with online kernel DL to mitigate this issue. Numerical tests verify the efficacy of the proposed strategies.
AB - Online kernel-based dictionary learning (DL) algorithms are considered, which perform DL on training data lifted to a high-dimensional feature space via a nonlinear mapping. Compared to batch versions, online algorithms require low computational complexity, essential for processing the Big Data, based on the stochastic gradient descent method. However, as with any kernel-based learning algorithms, the number of parameters needed to represent the desired dictionary is equal to the number of training samples, which incurs prohibitive memory requirement and computational complexity for large-scale datasets. In this work, appropriate sparsification and pruning strategies are combined with online kernel DL to mitigate this issue. Numerical tests verify the efficacy of the proposed strategies.
UR - http://www.scopus.com/inward/record.url?scp=85016326477&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85016326477&partnerID=8YFLogxK
U2 - 10.1109/ACSSC.2016.7869635
DO - 10.1109/ACSSC.2016.7869635
M3 - Conference contribution
AN - SCOPUS:85016326477
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 1535
EP - 1539
BT - Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Y2 - 6 November 2016 through 9 November 2016
ER -