Sciweavers

77 search results - page 4 / 16
» Exact Matrix Completion via Convex Optimization
Sort
View
JMLR
2008
169views more  JMLR 2008»
13 years 8 months ago
Multi-class Discriminant Kernel Learning via Convex Programming
Regularized kernel discriminant analysis (RKDA) performs linear discriminant analysis in the feature space via the kernel trick. Its performance depends on the selection of kernel...
Jieping Ye, Shuiwang Ji, Jianhui Chen
SIAMREV
2010
174views more  SIAMREV 2010»
13 years 3 months ago
Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
The affine rank minimization problem consists of finding a matrix of minimum rank that satisfies a given system of linear equality constraints. Such problems have appeared in the ...
Benjamin Recht, Maryam Fazel, Pablo A. Parrilo
CORR
2010
Springer
103views Education» more  CORR 2010»
13 years 8 months ago
Robust Matrix Decomposition with Outliers
Suppose a given observation matrix can be decomposed as the sum of a low-rank matrix and a sparse matrix (outliers), and the goal is to recover these individual components from th...
Daniel Hsu, Sham M. Kakade, Tong Zhang
CORR
2010
Springer
198views Education» more  CORR 2010»
13 years 5 months ago
Convex Graph Invariants
The structural properties of graphs are usually characterized in terms of invariants, which are functions of graphs that do not depend on the labeling of the nodes. In this paper ...
Venkat Chandrasekaran, Pablo A. Parrilo, Alan S. W...
MP
2010
135views more  MP 2010»
13 years 7 months ago
An inexact Newton method for nonconvex equality constrained optimization
Abstract We present a matrix-free line search algorithm for large-scale equality constrained optimization that allows for inexact step computations. For sufficiently convex problem...
Richard H. Byrd, Frank E. Curtis, Jorge Nocedal