Analyzing tensor power method dynamics in overcomplete regime

MaRDI QIDQ5361285zbMATH OpenFDO

Authors Animashree Anandkumar, Rong Ge, Majid Janzamin

Publication date 27 September 2017

Full work available at URL https://arxiv.org/abs/1411.1488, http://jmlr.csail.mit.edu/papers/v18/15-486.html

zbMATH Keywords

latent variable modelsovercomplete representationtensor decompositiontensor power iterationunsupervised learning

Mathematics Subject Classification ID

Numerical linear algebra (65F99) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Tensor decompositions for learning latent variable models
• Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT)
• Smoothed analysis of tensor decompositions
• Overcomplete order-3 tensor decomposition, blind deconvolution, and Gaussian mixture models
• Provable sparse tensor decomposition

Cited in

(12)

• Orthogonal and unitary tensor decomposition from an algebraic perspective
• Convergence rates of latent topic models under relaxed identifiability conditions
• A geometric analysis of phase retrieval
• Smoothed analysis for tensor methods in unsupervised learning
• On the optimization landscape of tensor decompositions
• When are overcomplete topic models identifiable? Uniqueness of tensor Tucker decompositions with structured sparsity
• On Tensors That Are Determined by Their Singular Tuples
• Smoothed analysis of tensor decompositions
• Average-case complexity of tensor decomposition for low-degree polynomials
• The Kikuchi hierarchy and tensor PCA
• Diagonal Gaussian mixture models and higher order tensor decompositions
• Spectral methods from tensor networks

This page was built for publication: Analyzing tensor power method dynamics in overcomplete regime

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5361285)