Joint support recovery under high-dimensional scaling: Benefits and perils of 1,-regularization, Poster W30
D

Sahand Negahban

M

artin J. Wainwright,

epartment of StatistUs , and Department of Electrical Engineering and Computer Sciences ic niversity of California, Berkeley, CA 94720-1770

1, relaxation for s = 0.1*p and  = 1, 0.7, 0.4, 0.1 1

0.8 Prob. success
=1

0.6
 = 0.7  = 0.4  = 0.1

0.4

0.2

0 0

1

2 3 Control parameter 

4

p = 128 p = 256 p = 512 5