Estimation of structured tensor models and recovery of low-rank tensors

Abstract : In the first part of this thesis, we formulate two methods for computing a canonical polyadic decomposition having linearly structured matrix factors (such as, e.g., Toeplitz or banded factors): a general constrained alternating least squares (CALS) algorithm and an algebraic solution for the case where all factors are circulant. Exact and approximate versions of the former method are studied. The latter method relies on a multidimensional discrete-time Fourier transform of the target tensor, which leads to a system of homogeneous monomial equations whose resolution provides the desired circulant factors. Our simulations show that combining these approaches yields a statistically efficient estimator, which is also true for other combinations of CALS in scenarios involving non-circulant factors. The second part of the thesis concerns low-rank tensor recovery (LRTR) and, in particular, the tensor completion (TC) problem. We propose an efficient algorithm, called SeMPIHT, employing sequentially optimal modal projections as its hard thresholding operator. Then, a performance bound is derived under usual restricted isometry conditions, which however yield suboptimal sampling bounds. Yet, our simulations suggest SeMPIHT obeys optimal sampling bounds for Gaussian measurements. Step size selection and gradual rank increase heuristics are also elaborated in order to improve performance. We also devise an imputation scheme for TC based on soft thresholding of a Tucker model core and illustrate its utility in completing real-world road traffic data acquired by an intelligent transportation
Document type :
Complete list of metadatas

Cited literature [192 references]  Display  Hide  Download
Contributor : Abes Star <>
Submitted on : Monday, February 13, 2017 - 5:19:09 PM
Last modification on : Thursday, December 19, 2019 - 3:50:05 AM
Long-term archiving on: Sunday, May 14, 2017 - 4:51:56 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01466776, version 1



José Henrique de Morais Goulart. Estimation of structured tensor models and recovery of low-rank tensors. Other. Université Côte d'Azur, 2016. English. ⟨NNT : 2016AZUR4147⟩. ⟨tel-01466776⟩



Record views


Files downloads