Canonical polyadic tensor decomposition in the presence of non Gaussian noise. Farias, R. C. & Comon, P. In 2015 23rd European Signal Processing Conference (EUSIPCO), pages 1321-1325, Aug, 2015.
Paper doi abstract bibtex In this paper we describe an estimator for the canonical polyadic (CP) tensor model using order statistics of the residuals. The estimator minimizes in an iterative and alternating fashion a dispersion function given by the weighted ranked absolute residuals. Specific choices of the weights lead to either equivalent or approximate versions of the least squares estimator, least absolute deviation estimator or least trimmed squares estimators. For different noise distributions, we present simulations comparing the performance of the pro posed algorithm with the standard least squares estimator. The simulated performance is equivalent in the Gaussian noise case and superior when the noise is distributed according to the Laplacian or Cauchy distributions.
@InProceedings{7362598,
author = {R. C. Farias and P. Comon},
booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},
title = {Canonical polyadic tensor decomposition in the presence of non Gaussian noise},
year = {2015},
pages = {1321-1325},
abstract = {In this paper we describe an estimator for the canonical polyadic (CP) tensor model using order statistics of the residuals. The estimator minimizes in an iterative and alternating fashion a dispersion function given by the weighted ranked absolute residuals. Specific choices of the weights lead to either equivalent or approximate versions of the least squares estimator, least absolute deviation estimator or least trimmed squares estimators. For different noise distributions, we present simulations comparing the performance of the pro posed algorithm with the standard least squares estimator. The simulated performance is equivalent in the Gaussian noise case and superior when the noise is distributed according to the Laplacian or Cauchy distributions.},
keywords = {Gaussian noise;iterative methods;least mean squares methods;signal processing;tensors;canonical polyadic tensor decomposition;nonGaussian noise;dispersion function;least squares estimator;least absolute deviation estimator;least trimmed squares estimators;Laplacian distributions;Cauchy distributions;Yttrium;Estimation;Least squares approximations;Robustness;Data models;Arrays;Tensile stress;Tensor decomposition;order statistics;non Gaussian noise;robust estimation},
doi = {10.1109/EUSIPCO.2015.7362598},
issn = {2076-1465},
month = {Aug},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570101111.pdf},
}
Downloads: 0
{"_id":"3Eb6YMgsSymGKxkPJ","bibbaseid":"farias-comon-canonicalpolyadictensordecompositioninthepresenceofnongaussiannoise-2015","authorIDs":[],"author_short":["Farias, R. C.","Comon, P."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["R.","C."],"propositions":[],"lastnames":["Farias"],"suffixes":[]},{"firstnames":["P."],"propositions":[],"lastnames":["Comon"],"suffixes":[]}],"booktitle":"2015 23rd European Signal Processing Conference (EUSIPCO)","title":"Canonical polyadic tensor decomposition in the presence of non Gaussian noise","year":"2015","pages":"1321-1325","abstract":"In this paper we describe an estimator for the canonical polyadic (CP) tensor model using order statistics of the residuals. The estimator minimizes in an iterative and alternating fashion a dispersion function given by the weighted ranked absolute residuals. Specific choices of the weights lead to either equivalent or approximate versions of the least squares estimator, least absolute deviation estimator or least trimmed squares estimators. For different noise distributions, we present simulations comparing the performance of the pro posed algorithm with the standard least squares estimator. The simulated performance is equivalent in the Gaussian noise case and superior when the noise is distributed according to the Laplacian or Cauchy distributions.","keywords":"Gaussian noise;iterative methods;least mean squares methods;signal processing;tensors;canonical polyadic tensor decomposition;nonGaussian noise;dispersion function;least squares estimator;least absolute deviation estimator;least trimmed squares estimators;Laplacian distributions;Cauchy distributions;Yttrium;Estimation;Least squares approximations;Robustness;Data models;Arrays;Tensile stress;Tensor decomposition;order statistics;non Gaussian noise;robust estimation","doi":"10.1109/EUSIPCO.2015.7362598","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570101111.pdf","bibtex":"@InProceedings{7362598,\n author = {R. C. Farias and P. Comon},\n booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},\n title = {Canonical polyadic tensor decomposition in the presence of non Gaussian noise},\n year = {2015},\n pages = {1321-1325},\n abstract = {In this paper we describe an estimator for the canonical polyadic (CP) tensor model using order statistics of the residuals. The estimator minimizes in an iterative and alternating fashion a dispersion function given by the weighted ranked absolute residuals. Specific choices of the weights lead to either equivalent or approximate versions of the least squares estimator, least absolute deviation estimator or least trimmed squares estimators. For different noise distributions, we present simulations comparing the performance of the pro posed algorithm with the standard least squares estimator. The simulated performance is equivalent in the Gaussian noise case and superior when the noise is distributed according to the Laplacian or Cauchy distributions.},\n keywords = {Gaussian noise;iterative methods;least mean squares methods;signal processing;tensors;canonical polyadic tensor decomposition;nonGaussian noise;dispersion function;least squares estimator;least absolute deviation estimator;least trimmed squares estimators;Laplacian distributions;Cauchy distributions;Yttrium;Estimation;Least squares approximations;Robustness;Data models;Arrays;Tensile stress;Tensor decomposition;order statistics;non Gaussian noise;robust estimation},\n doi = {10.1109/EUSIPCO.2015.7362598},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570101111.pdf},\n}\n\n","author_short":["Farias, R. C.","Comon, P."],"key":"7362598","id":"7362598","bibbaseid":"farias-comon-canonicalpolyadictensordecompositioninthepresenceofnongaussiannoise-2015","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570101111.pdf"},"keyword":["Gaussian noise;iterative methods;least mean squares methods;signal processing;tensors;canonical polyadic tensor decomposition;nonGaussian noise;dispersion function;least squares estimator;least absolute deviation estimator;least trimmed squares estimators;Laplacian distributions;Cauchy distributions;Yttrium;Estimation;Least squares approximations;Robustness;Data models;Arrays;Tensile stress;Tensor decomposition;order statistics;non Gaussian noise;robust estimation"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2015url.bib","creationDate":"2021-02-13T17:31:52.430Z","downloads":0,"keywords":["gaussian noise;iterative methods;least mean squares methods;signal processing;tensors;canonical polyadic tensor decomposition;nongaussian noise;dispersion function;least squares estimator;least absolute deviation estimator;least trimmed squares estimators;laplacian distributions;cauchy distributions;yttrium;estimation;least squares approximations;robustness;data models;arrays;tensile stress;tensor decomposition;order statistics;non gaussian noise;robust estimation"],"search_terms":["canonical","polyadic","tensor","decomposition","presence","non","gaussian","noise","farias","comon"],"title":"Canonical polyadic tensor decomposition in the presence of non Gaussian noise","year":2015,"dataSources":["eov4vbT6mnAiTpKji","knrZsDjSNHWtA9WNT"]}