HOSVD-Based Algorithm for Weighted Tensor Completion
arXiv:2003.08537
Abstract
Matrix completion, the problem of completing missing entries in a data matrix with low dimensional structure (such as rank), has seen many fruitful approaches and analyses. Tensor completion is the tensor analog, that attempts to impute missing tensor entries from similar low-rank type assumptions. In this paper, we study the tensor completion problem when the sampling pattern is deterministic and possibly non-uniform. We first propose an efficient weighted HOSVD algorithm for recovery of the underlying low-rank tensor from noisy observations and then derive the error bounds under a properly weighted metric. Additionally, the efficiency and accuracy of our algorithm are both tested using synthetic and real datasets in numerical simulations.
References in corpus (10)
- Tensor Decomposition for Signal Processing and Machine Learning
- Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
- Robust Low-rank Tensor Recovery: Models and Algorithms
- Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery
- Provable Tensor Factorization with Missing Data
- Matrix Completion via Max-Norm Constrained Optimization
- A Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completion
- Universal Matrix Completion
- Accelerated Structured Alternating Projections for Robust Spectrally Sparse Signal Recovery
- Matrix completion with deterministic pattern - a geometric perspective