Grassmannian Optimization for Online Tensor Completion and Tracking with the t-SVD
arXiv:2001.11419 · doi:10.1109/TSP.2022.3164837
Abstract
We propose a new fast streaming algorithm for the tensor completion problem of imputing missing entries of a low-tubal-rank tensor using the tensor singular value decomposition (t-SVD) algebraic framework. We show the t-SVD is a specialization of the well-studied block-term decomposition for third-order tensors, and we present an algorithm under this model that can track changing free submodules from incomplete streaming 2-D data. The proposed algorithm uses principles from incremental gradient descent on the Grassmann manifold of subspaces to solve the tensor completion problem with linear complexity and constant memory in the number of time samples. We provide a local expected linear convergence result for our algorithm. Our empirical results are competitive in accuracy but much faster in compute time than state-of-the-art tensor completion algorithms on real applications to recover temporal chemo-sensing and MRI data under limited sampling.
arXiv comment19 pages, 4 figures, 3 tables
References in corpus (10)
- Scalable Tensor Factorizations for Incomplete Data
- Subspace Learning and Imputation for Streaming Big Data Matrices and Tensors
- Provable Tensor Factorization with Missing Data
- Spectrum Cartography via Coupled Block-Term Tensor Decomposition
- Adaptive Sampling of RF Fingerprints for Fine-grained Indoor Localization
- Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems
- Online Low-Rank Tensor Subspace Tracking from Incomplete Data by CP Decomposition using Recursive Least Squares
- Stochastic Gradients for Large-Scale Tensor Decomposition
- Global Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation
- Robust Low-rank Matrix Completion via an Alternating Manifold Proximal Gradient Continuation Method