Convexity of the ℓ1-norm based sparsity measure with respect to the missing samples as variables.

Milos Brajovic Milos Dakovic Ljubisa Stankovic

Published in: MECO (2016)

Keyphrases

convexity measure
variable selection
group lasso
missing data
similarity measure
quadratic programming problems
mixed norm
training set
distance measure
data sets
sample points
random variables
compressive sampling
information theory
sparse representation
training samples
high dimensional
learning algorithm