Sciweavers

502 search results - page 35 / 101
» Principal Component Analysis for Sparse High-Dimensional Dat...
Sort
View
SDM
2009
SIAM
130views Data Mining» more  SDM 2009»
14 years 6 months ago
FuncICA for Time Series Pattern Discovery.
We introduce FuncICA, a new independent component analysis method for pattern discovery in inherently functional data, such as time series data. FuncICA can be considered an analo...
Alexander Gray, Nishant Mehta
NIPS
2000
13 years 10 months ago
Automatic Choice of Dimensionality for PCA
A central issue in principal component analysis (PCA) is choosing the number of principal components to be retained. By interpreting PCA as density estimation, this paper shows ho...
Thomas P. Minka
SDM
2007
SIAM
143views Data Mining» more  SDM 2007»
13 years 10 months ago
Less is More: Compact Matrix Decomposition for Large Sparse Graphs
Given a large sparse graph, how can we find patterns and anomalies? Several important applications can be modeled as large sparse graphs, e.g., network traffic monitoring, resea...
Jimeng Sun, Yinglian Xie, Hui Zhang, Christos Falo...
ORL
2011
13 years 3 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
ICMCS
2005
IEEE
138views Multimedia» more  ICMCS 2005»
14 years 2 months ago
Overcomplete ICA-based Manmade Scene Classification
Principal Component Analysis (PCA) has been widely used to extract features for pattern recognition problems such as object recognition. Oliva and Torralba used “spatial envelop...
Matthew Boutell, Jiebo Luo