A Well-Tempered Landscape for Non-convex Robust Subspace Recovery

zbMath1484.62063arXiv1706.03896MaRDI QIDQ4633049

Tyler Maunu, Teng Zhang, Gilad Lerman

Publication date: 2 May 2019

Full work available at URL: https://arxiv.org/abs/1706.03896

zbMATH Keywords

dimension reductionnon-convex optimizationoptimization on the Grassmannianrobust subspace recovery

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Nonparametric robustness (62G35)

Related Items (8)

On the rotational invariant \(L_1\)-norm PCA ⋮ Anisotropic Diffusion in Consensus-Based Optimization on the Sphere ⋮ Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution ⋮ Sampling-based dimension reduction for subspace approximation with outliers ⋮ Unnamed Item ⋮ On the robust PCA and Weiszfeld's algorithm ⋮ Robust PCA via regularized \textsc{Reaper} with a matrix-free proximal algorithm ⋮ Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods

Cites Work

• Unnamed Item
• Unnamed Item
• Geometric median and robust estimation in Banach spaces
• \(l_p\)-recovery of the most significant subspace among multiple subspaces with outliers
• Robust recovery of multiple subspaces by geometric \(l_{p}\) minimization
• Robust principal component analysis for functional data. (With comments)
• Riemannian geometry of Grassmann manifolds with a view on algorithmic computation
• On the distribution of the largest eigenvalue in principal components analysis
• Principal component analysis.
• A geometric analysis of subspace clustering with outliers
• Two proposals for robust PCA using semidefinite programming
• Spectral clustering based on local linear approximations
• The landscape of empirical risk for nonconvex losses
• The Grassmannian of affine subspaces
• Robust computation of linear models by convex relaxation
• The Littlewood-Offord problem and invertibility of random matrices
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Nonconvex Phase Synchronization
• Robust principal component analysis?
• Nonsmooth analysis on smooth manifolds
• An Analysis of the Total Approximation Problem in Separable Norms, and an Algorithm for the Total $l_1 $ Problem
• The Geometry of Algorithms with Orthogonality Constraints
• Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysis
• An elementary proof of a theorem of Johnson and Lindenstrauss
• Fast, robust and non-convex subspace recovery
• Probability and Computing
• Robust Statistics
• The Rotation of Eigenvectors by a Perturbation. III
• Some new bounds for singular values and eigenvalues of matrix products

This page was built for publication: A Well-Tempered Landscape for Non-convex Robust Subspace Recovery