A geometric analysis of subspace clustering with outliers

DOI10.1214/12-AOS1034zbMath1318.62217arXiv1112.4258MaRDI QIDQ1940771

Mahdi Soltanolkotabi, Emmanuel J. Candès

Publication date: 7 March 2013

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1112.4258

zbMATH Keywords

concentration of measure; spectral clustering; outlier detection; geometric functional analysis; subspace clustering; \(\ell_{1}\) minimization; duality in linear programming; properties of convex bodies

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

Related Items

Unnamed Item, Unnamed Item, Dimensionality-reduced subspace clustering, A Well-Tempered Landscape for Non-convex Robust Subspace Recovery, Unnamed Item, Unnamed Item, A general theory for subspace-sparse recovery, Unnamed Item, Learning Subspaces of Different Dimensions, Filtrated Algebraic Subspace Clustering, Relations Among Some Low-Rank Subspace Recovery Models, \(l_p\)-recovery of the most significant subspace among multiple subspaces with outliers, Rigorous restricted isometry property of low-dimensional subspaces, A new approach to two-view motion segmentation using global dimension minimization, A nonconvex formulation for low rank subspace clustering: algorithms and convergence analysis, Inference and mixture modeling with the elliptical Gamma distribution, Hybrid linear modeling via local best-fit flats, All-in-one robust estimator of the Gaussian mean, Subspace learning by \(\ell^0\)-induced sparsity, Minimal basis subspace representation: a unified framework for rigid and non-rigid motion segmentation, Robust subspace clustering, Reduced row echelon form and non-linear approximation for subspace segmentation and high-dimensional data clustering, Subspace segmentation by dense block and sparse representation, Beyond linear subspace clustering: a comparative study of nonlinear manifold clustering algorithms, Compressive Classification: Where Wireless Communications Meets Machine Learning

Cites Work

• Robust recovery of multiple subspaces by geometric \(l_{p}\) minimization
• Small ball probability and Dvoretzky's Theorem
• Multivariate analysis and Jacobi ensembles: largest eigenvalue, Tracy-Widom limits and rates of convergence
• Asymptotic theory of finite dimensional normed spaces. With an appendix by M. Gromov: Isoperimetric inequalities in Riemannian manifolds
• Nearest \(q\)-flat to \(m\) points
• \(k\)-plane clustering
• Isoradial bodies
• Hybrid linear modeling via local best-fit flats
• Convex Bodies with Few Faces
• On the isotropy constant of random convex sets
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• EXTREMAL PROPERTIES OF ORTHOGONAL PARALLELEPIPEDS AND THEIR APPLICATIONS TO THE GEOMETRY OF BANACH SPACES
• Computer Vision - ECCV 2004
• Metrics and models for handwritten character recognition