On tensor completion via nuclear norm minimization
From MaRDI portal
(Redirected from Publication:330103)
Abstract: Many problems can be formulated as recovering a low-rank tensor. Although an increasingly common task, tensor recovery remains a challenging problem because of the delicacy associated with the decomposition of higher order tensors. To overcome these difficulties, existing approaches often proceed by unfolding tensors into matrices and then apply techniques for matrix completion. We show here that such matricization fails to exploit the tensor structure and may lead to suboptimal procedure. More specifically, we investigate a convex optimization approach to tensor completion by directly minimizing a tensor nuclear norm and prove that this leads to an improved sample size requirement. To establish our results, we develop a series of algebraic and probabilistic techniques such as characterization of subdifferetial for tensor nuclear norm and concentration inequalities for tensor martingales, which may be of independent interests and could be useful in other tensor related problems.
Recommendations
Cites work
- A simpler approach to matrix completion
- Characterization of the subdifferential of some matrix norms
- Exact matrix completion via convex optimization
- Most tensor problems are NP-hard
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Some limit theorems for empirical processes (with discussion)
- Tensor Algebra and Multidimensional Harmonic Retrieval in Signal Processing for MIMO Radar
- Tensor Decompositions and Applications
- Tensor completion and low-\(n\)-rank tensor recovery via convex optimization
- Tensor-Based Formulation and Nuclear Norm Regularization for Multienergy Computed Tomography
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- User-friendly tail bounds for sums of random matrices
Cited in
(76)- scientific article; zbMATH DE number 7415122 (Why is no real title available?)
- Bayesian Dynamic Tensor Regression
- Highly entangled tensors
- Fiber sampling approach to canonical polyadic decomposition and application to tensor completion
- Matrix completion from a computational statistics perspective
- A tensor train approach for internet traffic data completion
- Sample complexity bounds for the local convergence of least squares approximation
- Block structure-based covariance tensor decomposition for group identification in matrix variables
- Approximating Tensor Norms via Sphere Covering: Bridging the Gap between Primal and Dual
- LOCUS: a regularized blind source separation method with low-rank structure for investigating brain connectivity
- Deterministic tensor completion with hypergraph expanders
- Exponential family tensor completion with auxiliary information
- Convergence bounds for empirical nonlinear least-squares
- Partially Observed Dynamic Tensor Response Regression
- Hybrid Kronecker Product Decomposition and Approximation
- Optimality conditions for Tucker low-rank tensor optimization
- Iterative tensor eigen rank minimization for low-rank tensor completion
- Rank minimization on tensor ring: an efficient approach for tensor decomposition and completion
- Efficient construction of tensor ring representations from sampling
- Riemannian conjugate gradient descent method for fixed multi rank third-order tensor completion
- Low tubal rank tensor recovery using the Bürer-Monteiro factorisation approach. Application to optical coherence tomography
- Spectral algorithms for tensor completion
- The geometry of rank-one tensor completion
- scientific article; zbMATH DE number 7164697 (Why is no real title available?)
- STORE: sparse tensor response regression and neuroimaging analysis
- Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees
- Biquadratic tensors, biquadratic decompositions, and norms of biquadratic tensors
- A concise proof to the spectral and nuclear norm bounds through tensor partitions
- Further results on tensor nuclear norms
- On polynomial time methods for exact low-rank tensor completion
- Conditions for the equivalence between the low-\(n\)-rank tensor recovery problem and its convex relaxation
- An approximation method of CP rank for third-order tensor completion
- A mixture of nuclear norm and matrix factorization for tensor completion
- Learning with tree tensor networks: complexity estimates and model selection
- Learning from comparisons and choices
- Near-optimal sample complexity for convex tensor completion
- Tensor principal component analysis via convex optimization
- Multilayer tensor factorization with applications to recommender systems
- Iterative methods based on soft thresholding of hierarchical tensors
- Tensor completion in hierarchical tensor representations
- An optimal statistical and computational framework for generalized tensor estimation
- Algebraic methods for tensor data
- Statistically optimal and computationally efficient low rank tensor completion from noisy entries
- Reshaped tensor nuclear norms for higher order tensor completion
- Hankel Matrix Nuclear Norm Regularized Tensor Completion for $N$-dimensional Exponential Signals
- Nonconvex tensor rank minimization and its applications to tensor recovery
- Dynamic tensor clustering
- $N$-Dimensional Tensor Completion for Nuclear Magnetic Resonance Relaxometry
- Spectral norm and nuclear norm of a third order tensor
- The Fréchet derivative of the tensor t-function
- Cross: efficient low-rank tensor completion
- Tensor methods for nonlinear matrix completion
- Factor Models for High-Dimensional Tensor Time Series
- Learning with tensors: a framework based on convex optimization and spectral regularization
- Scaled Coupled Norms and Coupled Higher-Order Tensor Completion
- Continuity, differentiability and semismoothness of generalized tensor functions
- Tensor completion by multi-rank via unitary transformation
- Low-rank approximation and completion of positive tensors
- Tensor Q-rank: new data dependent definition of tensor rank
- Block tensor train decomposition for missing data estimation
- Tensor theta norms and low rank recovery
- Learning diagonal Gaussian mixture models and incomplete tensor decompositions
- Tensor completion and low-\(n\)-rank tensor recovery via convex optimization
- Relations of the nuclear norm of a tensor and its matrix flattenings
- Inference for low-rank tensors -- no need to debias
- Tensor completion via a generalized transformed tensor t-product decomposition without t-SVD
- Symmetric tensor nuclear norms
- Tucker factorization with missing data with application to low-\(n\)-rank tensor completion
- ISLET: fast and optimal low-rank tensor regression via importance sketching
- On the tensor spectral \(p\)-norm and its dual norm via partitions
- Completely positive tensor recovery with minimal nuclear value
- Interpolatory tensorial reduced order models for parametric dynamical systems
- Nonconvex Low-Rank Tensor Completion from Noisy Data
- Convex coupled matrix and tensor completion
- scientific article; zbMATH DE number 7370581 (Why is no real title available?)
- On the equivalence between low-rank matrix completion and tensor rank
This page was built for publication: On tensor completion via nuclear norm minimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q330103)
