Published on Tue Oct 05 2010

Estimation of low-rank tensors via convex optimization

Ryota Tomioka, Kohei Hayashi, Hisashi Kashima

All approaches are formulated as convex minimization problems. The proposed approaches can automatically estimate the number of factors (rank) through the optimization. We show that the proposed convex optimization based approaches are more accurate in predictive performance.

0
0
0
Abstract

In this paper, we propose three approaches for the estimation of the Tucker decomposition of multi-way arrays (tensors) from partial observations. All approaches are formulated as convex minimization problems. Therefore, the minimum is guaranteed to be unique. The proposed approaches can automatically estimate the number of factors (rank) through the optimization. Thus, there is no need to specify the rank beforehand. The key technique we employ is the trace norm regularization, which is a popular approach for the estimation of low-rank matrices. In addition, we propose a simple heuristic to improve the interpretability of the obtained factorization. The advantages and disadvantages of three proposed approaches are demonstrated through numerical experiments on both synthetic and real world datasets. We show that the proposed convex optimization based approaches are more accurate in predictive performance, faster, and more reliable in recovering a known multilinear structure than conventional approaches.

Wed Aug 02 2017
Machine Learning
Exact Tensor Completion from Sparsely Corrupted Observations via Convex Optimization
This paper conducts a rigorous analysis for provable estimation of third-order tensors. We prove that by simply solving a convex program, one can recover an incoherent tensor exactly with overwhelming probability. Numerical experiments verify our theory and real-world applications demonstrate our algorithm's effectiveness.
0
0
0
Thu Oct 22 2020
Machine Learning
Robust Low-tubal-rank Tensor Completion based on Tensor Factorization and Maximum Correntopy Criterion
The goal of tensor completion is to recover a tensor from a subset of its entries. The low-tubal-rank was shown to give a valuable characterization of the inherent low-rank structure of a Tensor.
0
0
0
Sat Jun 19 2021
Machine Learning
Robust M-estimation-based Tensor Ring Completion: a Half-quadratic Minimization Approach
0
0
0
Tue Jul 21 2020
Machine Learning
Sparse Nonnegative Tensor Factorization and Completion with Noisy Observations
Because of sparsity and nonnegativity, the underling tensor is decomposed into one sparse nonnegative tensor and one nonnegative negative tensor. We show that the error bounds of the estimator of the proposed model can be established under general noise observations.
0
0
0
Mon Dec 04 2017
Machine Learning
A dual framework for low-rank tensor completion
The optimal solution is shown to lie on a Cartesian product of Riemannian manifolds. The experiments illustrate the efficacy of the proposed algorithm on several real-world datasets across applications.
0
0
0
Fri May 15 2015
Machine Learning
Optimal Low-Rank Tensor Recovery from Separable Measurements: Four Contractions Suffice
Tensors play a central role in many modern machine learning and signal processing applications. We present a computationally efficient algorithm, with rigorous and order-optimal sample complexity results for tensor recovery.
0
0
0