Sciweavers

2 search results - page 1 / 1
» Convex approximations to sparse PCA via Lagrangian duality
Sort
View
ORL
2011
12 years 11 months ago
Convex approximations to sparse PCA via Lagrangian duality
We derive a convex relaxation for cardinality constrained Principal Component Analysis (PCA) by using a simple representation of the L1 unit ball and standard Lagrangian duality. ...
Ronny Luss, Marc Teboulle
CORR
2011
Springer
202views Education» more  CORR 2011»
12 years 11 months ago
Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions
We analyze a class of estimators based on a convex relaxation for solving highdimensional matrix decomposition problems. The observations are the noisy realizations of the sum of ...
Alekh Agarwal, Sahand Negahban, Martin J. Wainwrig...