Sign inSign up
Restricted Eigen Condition for Heavy Tailed Designs thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Restricted Eigen Condition for Heavy Tailed Designs

Published on Aug 20, 20151640 Views

Arindam Banerjee

The restricted eigenvalue (RE) condition characterizes the sample complexity of accurate recovery in the context of high-dimensional estimators such as Lasso and Dantzig selector (Bickel et al., 200

COLT 2015 - Paris

Related categories

Active LearningComputational Learning TheoryOn-line LearningReinforcement LearningSemi-supervised Learning

Chapter list

Open Problem: Restricted Eigenvalue Condition for Heavy Tailed Designs00:00
Introduction00:01
Background: Restricted Isometry Property (RIP)02:13
Background: Restricted Eigenvalue (RE) Condition03:34
Heavy Tailed Designs: Small Ball Property04:37
Open Problem: RE Condition for Heavy Tailed Designs04:37