Tensor decompositions for learning latent variable models
From MaRDI portal
Publication:2934101
zbMath1319.62109arXiv1210.7559MaRDI QIDQ2934101
Rong Ge, Sham M. Kakade, Animashree Anandkumar, Matus Telgarsky, Daniel Hsu
Publication date: 8 December 2014
Full work available at URL: https://arxiv.org/abs/1210.7559
Asymptotic properties of parametric estimators (62F12) Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Multilinear algebra, tensor calculus (15A69)
Related Items
An optimal statistical and computational framework for generalized tensor estimation, Low tubal rank tensor recovery using the Bürer-Monteiro factorisation approach. Application to optical coherence tomography, Convergence rate analysis for the higher order power method in best rank one approximations of tensors, Ergodicity Coefficients for Higher-Order Stochastic Processes, Estimating multivariate latent-structure models, Inference for low-rank tensors -- no need to debias, Tensor decomposition for learning Gaussian mixtures from moments, Learning diagonal Gaussian mixture models and incomplete tensor decompositions, Subgroup-effects models for the analysis of personal treatment effects, A new method of moments for latent variable models, Newton Correction Methods for Computing Real Eigenpairs of Symmetric Tensors, Smoothed analysis for tensor methods in unsupervised learning, Successive Rank-One Approximations for Nearly Orthogonally Decomposable Symmetric Tensors, Unnamed Item, Unnamed Item, The set of orthogonal tensor trains, Unnamed Item, Statistically optimal and computationally efficient low rank tensor completion from noisy entries, Nonconvex Low-Rank Tensor Completion from Noisy Data, Statistical thresholds for tensor PCA, Low-rank, Orthogonally Decomposable Tensor Regression With Application to Visual Stimulus Decoding of fMRI Data, A note on the simultaneous Waring rank of monomials, On the identifiability of ternary forms, Robustness and Tractability for Non-convex M-estimators, Condition numbers for the tensor rank decomposition, Nonparametric estimation of non-exchangeable latent-variable models, Statistical limits of spiked tensor models, On the number of Waring decompositions for a generic polynomial vector, Greedy Approaches to Symmetric Orthogonal Tensor Decomposition, Effective Criteria for Specific Identifiability of Tensors and Forms, Orthogonal and unitary tensor decomposition from an algebraic perspective, Some inequalities on the spectral radius of nonnegative tensors, Learning Markov Models Via Low-Rank Optimization, Successive partial-symmetric rank-one algorithms for almost unitarily decomposable conjugate partial-symmetric tensors, Identifiability for a class of symmetric tensors, Unnamed Item, Unnamed Item, Unnamed Item, Using negative curvature in solving nonlinear programs, Low Rank Symmetric Tensor Approximations, Decomposing tensors into frames, Three decompositions of symmetric tensors have similar condition numbers, Singular vectors of orthogonally decomposable tensors, Detecting approximate replicate components of a high-dimensional random vector with latent structure, The Condition Number of Join Decompositions, Mixed membership Gaussians, On generic identifiability of symmetric tensors of subgeneric rank, The average condition number of most tensor rank decomposition problems is infinite, Lower bounds on the rank and symmetric rank of real tensors, Convergence rates of latent topic models under relaxed identifiability conditions, A Riemannian Trust Region Method for the Canonical Tensor Rank Approximation Problem, Eigenconfigurations of tensors, Optimal estimation of Gaussian mixtures via denoised method of moments, Approximate Matrix and Tensor Diagonalization by Unitary Transformations: Convergence of Jacobi-Type Algorithms, Anomaly detection in scientific data using joint statistical moments, Recovering Structured Probability Matrices, Spectral learning of weighted automata. A forward-backward perspective, Multiresolution Low-rank Tensor Formats, Estimating Higher-Order Moments Using Symmetric Tensor Decomposition, Reducing uncertainty of dynamic heterogeneous information networks: a fusing reconstructing approach, On a geometric method for the identifiability of forms, Efficient semiparametric estimation and model selection for multidimensional mixtures, Sequence Classification Using Third-Order Moments, Operator norm inequalities between tensor unfoldings on the partition lattice, On the subdifferential of symmetric convex functions of the spectrum for symmetric and orthogonally decomposable tensors, The Spacey Random Walk: A Stochastic Process for Higher-Order Data, On polynomial time methods for exact low-rank tensor completion, Unnamed Item, Unnamed Item, The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising, Bounds on strongly orthogonal ranks of tensors, Least squares moment identification of binary regression mixture models, Computing Tensor $Z$-Eigenvectors with Dynamical Systems, Robust high-dimensional factor models with applications to statistical machine learning, Moment identifiability of homoscedastic Gaussian mixtures, Optimal Sparse Singular Value Decomposition for High-Dimensional High-Order Data, Sparse random tensors: concentration, regularization and applications, Tensor-tensor products with invertible linear transforms, A Model-Based Embedding Technique for Segmenting Customers, Resonator Networks, 2: Factorization Performance and Capacity Compared to Optimization-Based Methods, An inexact augmented Lagrangian method for computing strongly orthogonal decompositions of tensors, Approximate minimization of weighted tree automata, Riemannian Newton optimization methods for the symmetric tensor approximation problem, Three-way clustering of multi-tissue multi-individual gene expression data using semi-nonnegative tensor decomposition, Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT), Tensor train spectral method for learning of hidden Markov models (HMM), An operator theoretic approach to nonparametric mixture models, Unnamed Item, Unnamed Item, Fast Moment Estimation for Generalized Latent Dirichlet Models, The Hitchhiker guide to: secant varieties and tensor decomposition, Comparison of Accuracy and Scalability of Gauss--Newton and Alternating Least Squares for CANDECOMC/PARAFAC Decomposition, Unnamed Item, Asymptotic behavior of large Gaussian correlated Wishart matrices, Unnamed Item, Smoothed tensor quantile regression estimation for longitudinal data, A spectral algorithm for latent Dirichlet allocation, Tensor-Structured Sketching for Constrained Least Squares, ISLET: Fast and Optimal Low-Rank Tensor Regression via Importance Sketching, Minimality and uniqueness for decompositions of specific ternary forms, Robust Eigenvectors of Symmetric Tensors, Orthogonal decomposition of tensor trains, Linear convergence of an alternating polar decomposition method for low rank orthogonal tensor approximations, Iterative hard thresholding for low CP-rank tensor models, Real eigenstructure of regular simplex tensors, A moment-matching metric for latent variable generative models, Marchenko–Pastur law with relaxed independence conditions, Statistical Inference, Learning and Models in Big Data, Identifiability for mixtures of centered Gaussians and sums of powers of quadratics, Identifiability of Hierarchical Latent Attribute Models, Alternating Mahalanobis Distance Minimization for Accurate and Well-Conditioned CP Decomposition, Approximate real symmetric tensor rank, On the stability of discrete-time homogeneous polynomial dynamical systems, When random tensors meet random matrices, Randomized Joint Diagonalization of Symmetric Matrices, Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization, Covariate-Assisted Sparse Tensor Completion, Absolute reconstruction for sums of powers of linear forms: degree 3 and beyond, A tensor-EM method for large-scale latent class analysis with binary responses, An algorithm for the non-identifiability of rank-3 tensors, Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals, Assigning topics to documents by successive projections, Learning Topic Models: Identifiability and Finite-Sample Analysis, Statistical mechanics of low-rank tensor decomposition, Lower Memory Oblivious (Tensor) Subspace Embeddings with Fewer Random Bits: Modewise Methods for Least Squares, Guarantees for Existence of a Best Canonical Polyadic Approximation of a Noisy Low-Rank Tensor, New Riemannian Preconditioned Algorithms for Tensor Completion via Polyadic Decomposition
