Computing a nonnegative matrix factorization -- provably

From MaRDI portal
Publication:5415472


DOI10.1145/2213977.2213994zbMath1286.15014arXiv1111.0952MaRDI QIDQ5415472

Rong Ge, Ankur Moitra, Sanjeev Arora, Ravindran Kannan

Publication date: 13 May 2014

Published in: Proceedings of the forty-fourth annual ACM symposium on Theory of computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1111.0952


15A23: Factorization of matrices


Related Items

Unnamed Item, Matrices of Bounded Psd Rank are Easy to Detect, Maximum Volume Inscribed Ellipsoid: A New Simplex-Structured Matrix Factorization Framework via Facet Enumeration and Convex Optimization, Toward Quantifying Vertex Similarity in Networks, Simplex-Structured Matrix Factorization: Sparsity-Based Identifiability and Provably Correct Algorithms, Provably Robust Blind Source Separation of Linear-Quadratic Near-Separable Mixtures, Multilinear Compressive Sensing and an Application to Convolutional Linear Networks, Unnamed Item, Unnamed Item, Statistical Methods for Minimax Estimation in Linear Models with Unknown Design Over Finite Alphabets, Refinement of Hottopixx Method for Nonnegative Matrix Factorization Under Noisy Separability, Nonnegative Matrix Factorization Via Archetypal Analysis, Recovering Structured Probability Matrices, Non-Negative Sparse Regression and Column Subset Selection with L1 Error, Parameterized Low-Rank Binary Matrix Approximation, Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization, Low Permutation-rank Matrices: Structural Properties and Noisy Completion, The Complexity of Positive Semidefinite Matrix Factorization, An Almost Optimal Algorithm for Computing Nonnegative Rank, Estimating Mixed Memberships With Sharp Eigenvector Deviations, Smoothed separable nonnegative matrix factorization, Analyzing Raman spectral data without separabiliy assumption, Robustness analysis of preconditioned successive projection algorithm for general form of separable NMF problem, Heuristics for exact nonnegative matrix factorization, Common information and unique disjointness, A polynomial-time algorithm for computing low CP-rank decompositions, Lower bounds on nonnegative rank via nonnegative nuclear norms, Tropical lower bounds for extended formulations, Positive semidefinite rank, Robust vertex enumeration for convex hulls in high dimensions, Convex nonnegative matrix factorization with manifold regularization, A very brief introduction to nonnegative tensors from the geometric viewpoint, Efficient preconditioning for noisy separable nonnegative matrix factorization problems by successive projection based low-rank approximations, DC-NMF: nonnegative matrix factorization based on divide-and-conquer for fast clustering and topic modeling, Multiscale blind source separation, On the geometric interpretation of the nonnegative rank, A geometric lower bound on the extension complexity of polytopes based on the \(f\)-vector, Factoring a band matrix over a semiring, Convex programming based spectral clustering, Minimal positive realizations: A survey, Parameterized low-rank binary matrix approximation, Robust subspace clustering, Methods for nonnegative matrix factorization based on low-rank cross approximations, An operator theoretic approach to nonparametric mixture models, Approximation algorithms for binary packing problems with quadratic constraints of low cp-rank decompositions, Enhanced matrix power function for cryptographic primitive construction, Approximate nonnegative rank is equivalent to the smooth rectangle bound, Non-negative matrix factorization under equality constraints -- a study of industrial source identification, SAGA: sparse and geometry-aware non-negative matrix factorization through non-linear local embedding, Trace Refinement in Labelled Markov Decision Processes, Computing a Nonnegative Matrix Factorization---Provably, Enhancing Pure-Pixel Identification Performance via Preconditioning, Approximation Limits of Linear Programs (Beyond Hierarchies)