Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT)

DOI10.1007/978-3-319-24486-0_2zbMath1471.62367OpenAlexW2274757334MaRDI QIDQ2835615

Sham M. Kakade, Rong Ge, Daniel Hsu, Matus Telgarsky, Anima Anandkumar

Publication date: 30 November 2016

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-319-24486-0_2

Mathematics Subject Classification ID

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

Convenient tail bounds for sums of random tensors, General tail bounds for random tensors summation: majorization approach, Eigenvectors of Orthogonally Decomposable Functions

Cites Work

• Unnamed Item
• Unnamed Item
• A spectral algorithm for learning hidden Markov models
• On exchangeable random variables and the statistics of large graphs and hypergraphs
• Asymptotic methods in statistical decision theory
• Full reconstruction of Markov models on evolutionary trees: identifiability and consistency.
• Independent component analysis, a new concept?
• Adaptive blind separation of independent sources: A deflation approach
• A spectral algorithm for latent Dirichlet allocation
• Eigenvalues of a real supersymmetric tensor
• Rank-One Approximation to High Order Tensors
• Tensor decompositions for learning latent variable models
• Learning mixtures of spherical gaussians
• Shifted Power Method for Computing Tensor Eigenpairs
• Numerical Optimization
• On the Best Rank-1 and Rank-(R₁ ,R₂ ,. . .,R_N) Approximation of Higher-Order Tensors
• Symmetric Tensors and Symmetric Tensor Rank
• Perturbation bounds in connection with singular value decomposition
• Learning nonsingular phylogenies and hidden Markov models
• Subtracting a best rank-1 approximation may increase tensor rank