Sparse principal component analysis via variable projection
From MaRDI portal
Publication:150980
DOI10.1137/18M1211350zbMATH Open1440.62231arXiv1804.00341OpenAlexW2795757876MaRDI QIDQ150980FDOQ150980
Authors: N. Benjamin Erichson, Peng Zheng, Krithika Manohar, Steven L. Brunton, J. Nathan Kutz, Aleksandr Y. Aravkin, N. Benjamin Erichson, Peng Zheng, Krithika Manohar, S. L. Brunton, Aleksandr Y. Aravkin, J. N. Kutz 
Publication date: 1 April 2018
Published in: SIAM Journal on Applied Mathematics (Search for Journal in Brave)
Abstract: Sparse principal component analysis (SPCA) has emerged as a powerful technique for modern data analysis, providing improved interpretation of low-rank structures by identifying localized spatial structures in the data and disambiguating between distinct time scales. We demonstrate a robust and scalable SPCA algorithm by formulating it as a value-function optimization problem. This viewpoint leads to a flexible and computationally efficient algorithm. Further, we can leverage randomized methods from linear algebra to extend the approach to the large-scale (big data) setting. Our proposed innovation also allows for a robust SPCA formulation which obtains meaningful sparse principal components in spite of grossly corrupted input data. The proposed algorithms are demonstrated using both synthetic and real world data, and show exceptional computational efficiency and diagnostic performance.
Full work available at URL: https://arxiv.org/abs/1804.00341
Recommendations
- Robust sparse principal component analysis
- Projection sparse principal component analysis: an efficient least squares method
- Sparse generalized principal component analysis for large-scale applications beyond Gaussianity
- Sparse principal component analysis via regularized low rank matrix approximation
- Sparse principal component analysis via fractional function regularity
Factor analysis and principal components; correspondence analysis (62H25) Generalized linear models (logistic models) (62J12) Randomized algorithms (68W20)
Cites Work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
- Constrained sparse Galerkin regression
- Least angle regression. (With discussion)
- Convergence of a block coordinate descent method for nondifferentiable minimization
- Variational Analysis
- Sparsity and Smoothness Via the Fused Lasso
- Regularization and Variable Selection Via the Elastic Net
- Model Selection and Estimation in Regression with Grouped Variables
- Generalized power method for sparse principal component analysis
- Robust principal component analysis?
- Optimal solutions for sparse principal component analysis
- Robust Statistics
- Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
- Sparse principal component analysis via regularized low rank matrix approximation
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- The immersed boundary method: a projection approach
- Sparse PCA: optimal rates and adaptive estimation
- A hierarchy of low-dimensional models for the transient and post-transient cylinder wake
- Sparse dynamics for partial differential equations
- Compressed modes for variational problems in mathematics and physics
- Linear dimensionality reduction: survey, insights, and generalizations
- Handbook of robust low-rank and sparse matrix decomposition. Applications in image and video processing
- Multiresolution dynamic mode decomposition
- Proximal splitting methods in signal processing
- Adaptive \(h\)-refinement for reduced-order models
- Network structure of two-dimensional decaying isotropic turbulence
- Randomized Algorithms for Matrices and Data
- Estimating nuisance parameters in inverse problems
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Cluster-based reduced-order modelling of a mixing layer
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Separable nonlinear least squares: the variable projection method and its applications
- Title not available (Why is that?)
- Procrustes Problems
- Variable projection methods for an optimized dynamic mode decomposition
- Efficient Quadratic Penalization Through the Partial Minimization Technique
- Data-Driven Sparse Sensor Placement for Reconstruction: Demonstrating the Benefits of Exploiting Known Patterns
- Why Are Big Data Matrices Approximately Low Rank?
- Decomposition into low-rank plus additive matrices for background/foreground separation: a review for a comparative evaluation with a large-scale dataset
- A minimization principle for the description of modes associated with finite-time instabilities
- RandNLA
- Improve robustness of sparse PCA by \(L_{1}\)-norm maximization
- Dynamically orthogonal field equations for continuous stochastic dynamical systems
Cited In (24)
- Bootstrapping the operator norm in high dimensions: error estimation for covariance matrices and sketching
- A generalized inertial proximal alternating linearized minimization method for nonconvex nonsmooth problems
- Multi-step-length gradient iterative method for separable nonlinear least squares problems.
- Sparse generalized principal component analysis for large-scale applications beyond Gaussianity
- Sparse principal component regression via singular value decomposition approach
- The sparse principal component analysis problem: optimality conditions and algorithms
- Shallow neural networks for fluid flow reconstruction with limited sensors
- Sparsifying the least-squares approach to PCA: comparison of lasso and cardinality constraint
- Numerical approximation of partial differential equations by a variable projection method with artificial neural networks
- Variable projection algorithms with sparse constraint for separable nonlinear models
- Sparse and integrative principal component analysis for multiview data
- sparsepca
- Sparse Variable PCA Using Geodesic Steepest Descent
- Separable nonlinear least-squares parameter estimation for complex dynamic systems
- An empirical comparison of two approaches for CDPCA in high-dimensional data
- Sparse Independent Component Analysis with an Application to Cortical Surface fMRI Data in Autism
- Detecting changes in the second moment structure of high-dimensional sensor-type data in a \(K\)-sample setting
- Sparse Principal Component Analysis via Axis-Aligned Random Projections
- A priori sparsification of Galerkin models
- Robust sparse principal component analysis
- Spike and slab Bayesian sparse principal component analysis
- Title not available (Why is that?)
- Solving sparse principal component analysis with global support
- Feature grouping and sparse principal component analysis with truncated regularization
Uses Software
This page was built for publication: Sparse principal component analysis via variable projection
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q150980)
