Sparse Principal Component Analysis

By Hui Zou, Trevor J. Hastie, Robert Tibshirani. 2006

3,331 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) (2017, background): “While option 1 offers simplicity as the explanation is embedded in the model (Kim et al., 2014; Doshi-Velez et al., 2015; Tibshirani, 1994; Zou et al., 2004; Ustun et al., 2013; Caruana et al., 2015), this option might be costly for users who already have a working high performance model.”
Principal Component Analysis (2003, neutral): “The types and contents of volatile flavor compounds in duck meat are affected by many factors (Zhen et al., 2022).”
Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation (2013, methodology): “The sparse PCA problem ([31]) is a standard and well-known statistical estimation problem, defined as follows: We are given an i.”
Bayesian group factor analysis with structured sparsity (2016, methodology): “Imposing element-wise sparsity in latent factor models has been studied through regularization via 1 type penalties (Zou et al., 2006; Witten et al., 2009; Salzmann et al., 2010).”
Online Learning for Matrix Factorization and Sparse Coding (2009, neutral): “…is to alternate between the two variables, minimizing over one while keeping the other one ﬁxed, as proposed by Lee et al. (2007) (see also Engan et al. 1999 and Aharon et al. 2006, who use ℓ 0 rather than ℓ 1 penalties, or Zou et al. 2006 for the problem of sparse principal component analysis).”
Sparse localized deformation components (2013, methodology): “It takes inspiration from matrix decomposition methods such as Non-Negative Matrix Factorization (NMF), Robust PCA, and Sparse PCA, that have recently been very popular in machine learning, image processing and computer vision.”
Methods of integrating data to uncover genotype–phenotype interactions (2015, methodology): “This can lead to spurious associations if not adjusted for appropriately. component analysis (PCA) 30,34 , factor analysis 30 and genetic algorithms 35 .”
The functional diversity of retinal ganglion cells in the mouse (2016, positive): “We used sparse principle component analysis 54 , as implemented in the SpaSM toolbox by K. Sjöstrang et al. (http://www2.imm.dtu.dk/projects/spasm/), to extract sparse response features from the responses to the chirp, colour, and moving bar stimulus, resulting in features which use only a small…”
Principal Component Analysis (2018, methodology): “To overcome these issues, sparse PCA (SPCA) was developed to ensure that less significant loadings be exactly zero [Zou et al. 2006].”
Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification (2013, background): “To effectively apply a supervised learning method in the second stage, the dimension of these features is reduced to 400 by PCA 2 .”
Full regularization path for sparse principal component analysis (2007, positive): “The SPCA algorithm, which is based on the representation of PCA as a regression-type optimization problem (Zou et al., 2004), allows the application of the LASSO (Tibshirani, 1996), a penalization technique based on the l1 norm.”
Least squares linear discriminant analysis (2007, background): “Jolli.e, I., & Uddin, M. (2003).”
Sparse probabilistic projections (2008, methodology): “In recent years, several methods for sparse PCA have been designed to find projections which retain maximal variance, while enforcing many entries of the projection matrix to be zero [20, 6].”
Interpolation and denoising of high-dimensional seismic data by learning a tight frame (2015, methodology): “We remove the constant item and get an equivalent maximization problem as (6): 14 argmax A Tr(AV GT ), s.t. ATA = I (7) The theorem in Zou et al. (2006) helps solve (7): Theorem 0.1.”
Truncated power method for sparse eigenvalue problems (2011, methodology): “For instance, Zou et al. (2006) formulated sparse PCA as a regression-type optimization problem and imposed the Lasso (Tibshirani, 1996) penalty on the regression coeﬃcients.”