Home > Research > Publications & Outputs > Tropical geometric tools for machine learning

Electronic data

Links

Text available via DOI:

View graph of relations

Tropical geometric tools for machine learning: the TML package

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Tropical geometric tools for machine learning: the TML package. / Barnhill, D.; Yoshida, R.; Aliatimis, G. et al.
In: Journal of Software for Algebra and Geometry, Vol. 14, No. 1, 05.10.2024, p. 133-174.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Barnhill, D, Yoshida, R, Aliatimis, G & Miura, K 2024, 'Tropical geometric tools for machine learning: the TML package', Journal of Software for Algebra and Geometry, vol. 14, no. 1, pp. 133-174. https://doi.org/10.2140/jsag.2024.14.133

APA

Barnhill, D., Yoshida, R., Aliatimis, G., & Miura, K. (2024). Tropical geometric tools for machine learning: the TML package. Journal of Software for Algebra and Geometry, 14(1), 133-174. https://doi.org/10.2140/jsag.2024.14.133

Vancouver

Barnhill D, Yoshida R, Aliatimis G, Miura K. Tropical geometric tools for machine learning: the TML package. Journal of Software for Algebra and Geometry. 2024 Oct 5;14(1):133-174. doi: 10.2140/jsag.2024.14.133

Author

Barnhill, D. ; Yoshida, R. ; Aliatimis, G. et al. / Tropical geometric tools for machine learning : the TML package. In: Journal of Software for Algebra and Geometry. 2024 ; Vol. 14, No. 1. pp. 133-174.

Bibtex

@article{56889ac9a6624422b96dcbb19df72137,
title = "Tropical geometric tools for machine learning: the TML package",
abstract = "In the last decade, developments in tropical geometry have provided a number of uses directly applicable to problems in statistical learning. The TML package is the first R package which contains a comprehensive set of tools and methods used for basic computations related to tropical convexity, visualization of tropically convex sets, as well as supervised and unsupervised learning models using the tropical metric under the max-plus algebra over the tropical projective torus. Primarily, the TML package employs a Hit-and-Run Markov chain Monte Carlo sampler in conjunction with the tropical metric as its main tool for statistical inference. In addition to basic computation and various applications of the tropical HAR sampler, we also focus on several supervised and unsupervised methods incorporated in the TML package including tropical principal component analysis, tropical logistic regression and tropical kernel density estimation.",
keywords = "tropical data science, tropical geometry, tropical machine learning",
author = "D. Barnhill and R. Yoshida and G. Aliatimis and K. Miura",
note = "Export Date: 30 October 2024",
year = "2024",
month = oct,
day = "5",
doi = "10.2140/jsag.2024.14.133",
language = "English",
volume = "14",
pages = "133--174",
journal = "Journal of Software for Algebra and Geometry",
number = "1",

}

RIS

TY - JOUR

T1 - Tropical geometric tools for machine learning

T2 - the TML package

AU - Barnhill, D.

AU - Yoshida, R.

AU - Aliatimis, G.

AU - Miura, K.

N1 - Export Date: 30 October 2024

PY - 2024/10/5

Y1 - 2024/10/5

N2 - In the last decade, developments in tropical geometry have provided a number of uses directly applicable to problems in statistical learning. The TML package is the first R package which contains a comprehensive set of tools and methods used for basic computations related to tropical convexity, visualization of tropically convex sets, as well as supervised and unsupervised learning models using the tropical metric under the max-plus algebra over the tropical projective torus. Primarily, the TML package employs a Hit-and-Run Markov chain Monte Carlo sampler in conjunction with the tropical metric as its main tool for statistical inference. In addition to basic computation and various applications of the tropical HAR sampler, we also focus on several supervised and unsupervised methods incorporated in the TML package including tropical principal component analysis, tropical logistic regression and tropical kernel density estimation.

AB - In the last decade, developments in tropical geometry have provided a number of uses directly applicable to problems in statistical learning. The TML package is the first R package which contains a comprehensive set of tools and methods used for basic computations related to tropical convexity, visualization of tropically convex sets, as well as supervised and unsupervised learning models using the tropical metric under the max-plus algebra over the tropical projective torus. Primarily, the TML package employs a Hit-and-Run Markov chain Monte Carlo sampler in conjunction with the tropical metric as its main tool for statistical inference. In addition to basic computation and various applications of the tropical HAR sampler, we also focus on several supervised and unsupervised methods incorporated in the TML package including tropical principal component analysis, tropical logistic regression and tropical kernel density estimation.

KW - tropical data science

KW - tropical geometry

KW - tropical machine learning

U2 - 10.2140/jsag.2024.14.133

DO - 10.2140/jsag.2024.14.133

M3 - Journal article

VL - 14

SP - 133

EP - 174

JO - Journal of Software for Algebra and Geometry

JF - Journal of Software for Algebra and Geometry

IS - 1

ER -