When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity
From MaRDI portal
Publication:2788378
zbMath1351.68202arXiv1308.2853MaRDI QIDQ2788378
Daniel Hsu, Sham M. Kakade, Animashree Anandkumar, Majid Janzamin
Publication date: 19 February 2016
Full work available at URL: https://arxiv.org/abs/1308.2853
Estimation in multivariate analysis (62H12) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Learning and adaptive systems in artificial intelligence (68T05)
Related Items
Multilinear PageRank, Unnamed Item, An algorithm for the non-identifiability of rank-3 tensors, Identifiability of nonparametric mixture models and Bayes optimal clustering, Bayesian analysis of dynamic linear topic models, Identifiability of homogeneous polynomials and Cremona transformations, Identifiability of Complete Dictionary Learning
