Two proposals for robust PCA using semidefinite programming
From MaRDI portal
Abstract: The performance of principal component analysis (PCA) suffers badly in the presence of outliers. This paper proposes two novel approaches for robust PCA based on semidefinite programming. The first method, maximum mean absolute deviation rounding (MDR), seeks directions of large spread in the data while damping the effect of outliers. The second method produces a low-leverage decomposition (LLD) of the data that attempts to form a low-rank model for the data by separating out corrupted observations. This paper also presents efficient computational methods for solving these SDPs. Numerical experiments confirm the value of these new techniques.
Recommendations
Cites work
- A dual algorithm for the solution of nonlinear variational problems via finite element approximation
- A framework for robust subspace learning
- A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
- Algorithm 851
- Approximating the Cut-Norm via Grothendieck's Inequality
- Asymptotic distributions of principal components based on robust dispersions
- Characterization of the subdifferential of some matrix norms
- Computing the norm ∥A∥∞,1 is NP-hard∗
- Convex Analysis
- Graph implementations for nonsmooth convex programs
- High breakdown estimators for principal components: the projection-pursuit approach revis\-ited
- scientific article; zbMATH DE number 3124239 (Why is no real title available?)
- scientific article; zbMATH DE number 3944534 (Why is no real title available?)
- scientific article; zbMATH DE number 45410 (Why is no real title available?)
- scientific article; zbMATH DE number 3574917 (Why is no real title available?)
- scientific article; zbMATH DE number 3005966 (Why is no real title available?)
- scientific article; zbMATH DE number 1821102 (Why is no real title available?)
- scientific article; zbMATH DE number 802854 (Why is no real title available?)
- scientific article; zbMATH DE number 3320125 (Why is no real title available?)
- Introduction to linear regression analysis.
- Local minima and convergence in low-rank semidefinite programming
- On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
- Optimal outlier removal in high-dimensional
- Principal component analysis based on robust estimators of the covariance or correlation matrix: influence functions and efficiencies
- Projection-Pursuit Approach to Robust Dispersion Matrices and Principal Components: Primary Theory and Monte Carlo
- Rank-Sparsity Incoherence for Matrix Decomposition
- Robust Estimation of Dispersion Matrices and Principal Components
- Robust PCA via Outlier Pursuit
- Robust principal component analysis for functional data. (With comments)
- Robust Statistics
- Robust Statistics
- Robust Statistics
- Semidefinite relaxation and nonconvex quadratic optimization
- Signal Recovery by Proximal Forward-Backward Splitting
- Sparse solutions to linear inverse problems with multiple measurement vectors
- Sums of random symmetric matrices and quadratic optimization under orthogonality constraints
Cited in
(31)- Simplicial faces of the set of correlation matrices
- On the robust PCA and Weiszfeld's algorithm
- Robust PCA via regularized \textsc{Reaper} with a matrix-free proximal algorithm
- On the rotational invariant \(L_1\)-norm PCA
- Set membership identification of switched linear systems with known number of subsystems
- Robust computation of linear models by convex relaxation
- Learning linear PCA with convex semi-definite programming
- Robust PCA and pairs of projections in a Hilbert space
- Robust principal component analysis: a factorization-based approach with linear complexity
- Two-stage convex relaxation approach to least squares loss constrained low-rank plus sparsity optimization problems
- Robust _1 approaches to computing the geometric median and principal and independent components
- Robust principal component analysis?
- The FastHCS algorithm for robust PCA
- Applications of gauge duality in robust principal component analysis and semidefinite programming
- Robust principal component analysis via ES-algorithm
- Sharp recovery bounds for convex demixing, with applications
- Noisy matrix decomposition via convex relaxation: optimal rates in high dimensions
- Robust subspace recovery by Tyler's M-estimator
- A well-tempered landscape for non-convex robust subspace recovery
- l_p-recovery of the most significant subspace among multiple subspaces with outliers
- Optimization for L1-Norm Error Fitting via Data Aggregation
- Principal component analysis for α-stable vectors
- Majorization-Minimization on the Stiefel Manifold With Application to Robust Sparse PCA
- Robust Singular Value Decompositions: A New Approach to Projection Pursuit
- Relations among some low-rank subspace recovery models
- A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers
- On the minimax spherical designs
- Linear Convergence of a Proximal Alternating Minimization Method with Extrapolation for \(\boldsymbol{\ell_1}\) -Norm Principal Component Analysis
- Adaptive and robust multi-task learning
- Two-stage convex relaxation approach to low-rank and sparsity regularized least squares loss
- Optimization on the quaternion Stiefel manifold with applications. II: L1-QPCA
This page was built for publication: Two proposals for robust PCA using semidefinite programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1952221)
