On tensor completion via nuclear norm minimization

DOI10.1007/s10208-015-9269-5zbMath1378.90066arXiv1405.1773OpenAlexW1885765327MaRDI QIDQ330103

Publication date: 24 October 2016

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1405.1773

zbMATH Keywords

matrix completion convex optimization problem concentration inequality dual certificate tensor completion low-rank tensor nuclear norm minimization subfifferential

Mathematics Subject Classification ID

Convex programming (90C25) Approximation methods and heuristics in mathematical programming (90C59) Miscellaneous inequalities involving matrices (15A45)

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 bounds for empirical nonlinear least-squares, Inference for low-rank tensors -- no need to debias, Learning diagonal Gaussian mixture models and incomplete tensor decompositions, Learning with tree tensor networks: complexity estimates and model selection, Completely positive tensor recovery with minimal nuclear value, Interpolatory tensorial reduced order models for parametric dynamical systems, Highly entangled tensors, Statistically optimal and computationally efficient low rank tensor completion from noisy entries, Nonconvex Low-Rank Tensor Completion from Noisy Data, An approximation method of CP rank for third-order tensor completion, Iterative methods based on soft thresholding of hierarchical tensors, Continuity, differentiability and semismoothness of generalized tensor functions, Rank minimization on tensor ring: an efficient approach for tensor decomposition and completion, The Geometry of Rank-One Tensor Completion, Tensor completion by multi-rank via unitary transformation, LOCUS: a regularized blind source separation method with low-rank structure for investigating brain connectivity, Partially Observed Dynamic Tensor Response Regression, $N$-Dimensional Tensor Completion for Nuclear Magnetic Resonance Relaxometry, Unnamed Item, Iterative tensor eigen rank minimization for low-rank tensor completion, Hybrid Kronecker Product Decomposition and Approximation, Bayesian Dynamic Tensor Regression, Further results on tensor nuclear norms, The Fréchet derivative of the tensor t-function, Approximating Tensor Norms via Sphere Covering: Bridging the Gap between Primal and Dual, Optimality conditions for Tucker low-rank tensor optimization, Factor Models for High-Dimensional Tensor Time Series, Symmetric Tensor Nuclear Norms, Scaled Coupled Norms and Coupled Higher-Order Tensor Completion, Nonconvex tensor rank minimization and its applications to tensor recovery, Cross: efficient low-rank tensor completion, Algebraic Methods for Tensor Data, Multilayer tensor factorization with applications to recommender systems, Deterministic Tensor Completion with Hypergraph Expanders, Block tensor train decomposition for missing data estimation, On polynomial time methods for exact low-rank tensor completion, Unnamed Item, A concise proof to the spectral and nuclear norm bounds through tensor partitions, Subspace estimation from unbalanced and incomplete data matrices: ${\ell_{2,\infty}}$ statistical guarantees, Biquadratic tensors, biquadratic decompositions, and norms of biquadratic tensors, Dynamic Tensor Clustering, Tensor theta norms and low rank recovery, Reshaped tensor nuclear norms for higher order tensor completion, On the tensor spectral $p$-norm and its dual norm via partitions, Fiber Sampling Approach to Canonical Polyadic Decomposition and Application to Tensor Completion, Tensor Q-rank: new data dependent definition of tensor rank, Spectral norm and nuclear norm of a third order tensor, Efficient Construction of Tensor Ring Representations from Sampling, Riemannian conjugate gradient descent method for fixed multi rank third-order tensor completion, Unnamed Item, Unnamed Item, Tensor completion via a generalized transformed tensor t-product decomposition without t-SVD, Relations of the nuclear norm of a tensor and its matrix flattenings, ISLET: Fast and Optimal Low-Rank Tensor Regression via Importance Sketching

Cites Work