Statistical thresholds for tensor PCA

DOI10.1214/19-AAP1547zbMath1461.62087arXiv1812.03403MaRDI QIDQ2657928

Patrick Lopatto, Léo Miolane, Aukosh Jagannath

Publication date: 18 March 2021

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

Full work available at URL: https://arxiv.org/abs/1812.03403

zbMATH Keywords

principal component analysis (PCA)spherical spin glassesBBP transitiontensor principal component analysisspiked matrixspiked tensor

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Factor analysis and principal components; correspondence analysis (62H25) Nonparametric hypothesis testing (62G10)

Related Items (7)

Sharp complexity asymptotics and topological trivialization for the (p, k) spiked tensor model ⋮ Unnamed Item ⋮ When random tensors meet random matrices ⋮ Long random matrices and tensor unfolding ⋮ High‐dimensional limit theorems for SGD: Effective dynamics and critical scaling ⋮ The overlap gap property in principal submatrix recovery ⋮ Notes on computational hardness of hypothesis testing: predictions using the low-degree likelihood ratio

Cites Work

• Unnamed Item
• Unnamed Item
• Limits of spiked random matrices. I
• The Aizenman-Sims-Starr scheme and Parisi formula for mixed \(p\)-spin spherical models
• Parisi formula, disorder chaos and fluctuation for the ground state energy in the spherical mixed \(p\)-spin models
• Low temperature asymptotics of spherical mean field spin glasses
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• Algorithmic thresholds for tensor PCA
• The largest eigenvalue of small rank perturbations of Hermitian random matrices
• Exact solution of the gauge symmetric \(p\)-spin glass model on a complete graph
• Free energy of the spherical mean field model
• Cube root asymptotics
• Cavity method in the spherical SK model
• The largest eigenvalues of finite rank deformation of large Wigner matrices: Convergence and nonuniversality of the fluctuations
• Spectral gap estimates in mean field spin glasses
• Fundamental limits of symmetric low-rank matrix estimation
• Optimality and sub-optimality of PCA. I: Spiked random matrix models
• On the distribution of the largest eigenvalue in principal components analysis
• Large deviations of the extreme eigenvalues of random deformations of matrices
• Statistical limits of spiked tensor models
• The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference
• Phase transition in the spiked random tensor with Rademacher prior
• On the overlap in the multiple spherical SK models
• Large deviations for the largest eigenvalue of rank one deformations of Gaussian ensembles
• The largest eigenvalue of rank one deformation of large Wigner matrices
• Eigenvalues of large sample covariance matrices of spiked population models
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• On the principal components of sample covariance matrices
• Tensor decompositions for learning latent variable models
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• Mutual Information and Minimum Mean-Square Error in Gaussian Channels
• The eigenvalue spectrum of a large symmetric random matrix
• p> 2 spin glasses with first-order ferromagnetic transitions
• Multispin Ising spin glasses with ferromagnetic interactions
• Asymptotic mutual information for the balanced binary stochastic block model
• Information-Theoretic Bounds and Phase Transitions in Clustering, Sparse PCA, and Submatrix Localization
• The Sherrington-Kirkpatrick Model
• The Landscape of the Spiked Tensor Model
• On the Limitation of Spectral Methods: From the Gaussian Hidden Clique Problem to Rank One Perturbations of Gaussian Tensors
• Random Fields and Geometry
• Fast spectral algorithms from sum-of-squares proofs: tensor decomposition and planted sparse vectors
• Most Tensor Problems Are NP-Hard
• Envelope Theorems for Arbitrary Choice Sets
• Mean Field Models for Spin Glasses

This page was built for publication: Statistical thresholds for tensor PCA