A New Convex Relaxation for Tensor Completion
arXiv:1307.4653
Abstract
We study the problem of learning a tensor from a set of linear measurements. A prominent methodology for this problem is based on a generalization of trace norm regularization, which has been used extensively for learning low rank matrices, to the tensor setting. In this paper, we highlight some limitations of this approach and propose an alternative convex relaxation on the Euclidean ball. We then describe a technique to solve the associated regularization problem, which builds upon the alternating direction method of multipliers. Experiments on one synthetic dataset and two real datasets indicate that the proposed method improves significantly over tensor trace norm regularization in terms of estimation error, while remaining computationally tractable.
Cited by in corpus (18)
- Quantum machine learning: a classical perspective
- Parallel matrix factorization for low-rank tensor completion
- A General Analysis of the Convergence of ADMM
- Self-Supervised Nonlinear Transform-Based Tensor Nuclear Norm for Multi-Dimensional Image Recovery
- A statistical model for tensor PCA
- Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
- T2LR-Net: An unrolling network learning transformed tensor low-rank prior for dynamic MR image reconstruction
- Fundamental Conditions for Low-CP-Rank Tensor Completion
- Characterization of Deterministic and Probabilistic Sampling Patterns for Finite Completability of Low Tensor-Train Rank Tensor
- Provable Sparse Tensor Decomposition
- Scaled Nuclear Norm Minimization for Low-Rank Tensor Completion
- Deterministic and Probabilistic Conditions for Finite Completability of Low-Tucker-Rank Tensor
- Von Neumann's inequality for tensors
- Riemannian Tensor Completion with Side Information
- Dynamic Tensor Clustering
- Regularized Orthogonal Tensor Decompositions for Multi-Relational Learning
- Sensing tensors with Gaussian filters
- Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI