EUVIMEDEUVIMED entdecken
Crossref

Elliptically Contoured Tensor-variate Distributions with Application to Image Learning

Carlos Llosa-Vite, Ranjan Maitra

ACM Transactions on Probabilistic Machine Learning · 2025

DOI: 10.1145/3675161 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Probabilistic Machine Learning, 2025. Verfasst von Carlos Llosa-Vite und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Institute of Justice, National Institute of Biomedical Imaging and Bioengineering, Sandia National Laboratories.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Statistical analysis of tensor-valued data has largely used the tensor-variate normal (TVN) distribution that may be inadequate for data arising from distributions with heavier or lighter tails. We study a general family of elliptically contoured (EC) TV distributions and derive its characterizations, moments, marginal, and conditional distributions. We describe procedures for maximum likelihood estimation from data that are (1) uncorrelated draws from an EC distribution, (2) from a scale mixture of the TVN distribution, and (3) from an underlying but unknown EC distribution, for which we extend Tyler’s robust estimator. A detailed simulation study highlights the benefits of choosing an EC distribution over the TVN for heavier-tailed data. We develop TV classification rules using discriminant analysis and EC errors and show that they better predict cats and dogs from images in the Animal Faces-HQ dataset than the TVN-based rules. A novel tensor-on-tensor regression and TV analysis of variance (TANOVA) framework under EC errors is also demonstrated to better characterize gender, age, and ethnic origin than the usual TVN-based TANOVA in the celebrated labeled faces of the wild dataset.

Förderung

  • National Institute of Justice
  • National Institute of Biomedical Imaging and Bioengineering
  • Sandia National Laboratories
  • National Institute of Food and Agriculture

Zitieren

APA

Llosa-Vite, C., & Maitra, R. (2025). Elliptically Contoured Tensor-variate Distributions with Application to Image Learning. ACM Transactions on Probabilistic Machine Learning. https://doi.org/10.1145/3675161

Vancouver

Llosa-Vite C, Maitra R. Elliptically Contoured Tensor-variate Distributions with Application to Image Learning. ACM Transactions on Probabilistic Machine Learning. 2025. doi:10.1145/3675161

BibTeX
@article{LlosaVite2025,
  author = {Llosa-Vite, Carlos and Maitra, Ranjan},
  title = {Elliptically Contoured Tensor-variate Distributions with Application to Image Learning},
  journal = {ACM Transactions on Probabilistic Machine Learning},
  year = {2025},
  doi = {10.1145/3675161}
}
Kostenlos starten →