Tropical Support Vector Machines: Evaluations and Extension to Function Spaces

DOI10.1016/J.NEUNET.2022.10.002MaRDI QIDQ6359200zbMATH OpenFDO

Authors Ruriko Yoshida, Misaki Takamori, Hideyuki Matsumoto, Keiji Miura

Publication date 27 January 2021

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1016/J.NEUNET.2022.10.002

Mathematics Subject Classification ID

Statistics (62-XX) Learning and adaptive systems in artificial intelligence (68T05) Algebraic geometry (14-XX) Linear and multilinear algebra; matrix theory (15-XX)

Abstract: Support Vector Machines (SVMs) are one of the most popular supervised learning models to classify using a hyperplane in an Euclidean space. Similar to SVMs, tropical SVMs classify data points using a tropical hyperplane under the tropical metric with the max-plus algebra. In this paper, first we show generalization error bounds of tropical SVMs over the tropical projective torus. While the generalization error bounds attained via Vapnik-Chervonenkis (VC) dimensions in a distribution-free manner still depend on the dimension, we also show numerically and theoretically by extreme value statistics that the tropical SVMs for classifying data points from two Gaussian distributions as well as empirical data sets of different neuron types are fairly robust against the curse of dimensionality. Extreme value statistics also underlie the anomalous scaling behaviors of the tropical distance between random vectors with additional noise dimensions. Finally, we define tropical SVMs over a function space with the tropical metric.

Recommendations

• Robust learning and generalization with support vector machines.
• Support Vector Machines
• Tropical reproducing kernels and optimization
• scientific article; zbMATH DE number 2205906
• A tutorial on ν‐support vector machines

Cites work

• scientific article; zbMATH DE number 3141621 (Why is no real title available?)
• scientific article; zbMATH DE number 1983334 (Why is no real title available?)
• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• scientific article; zbMATH DE number 1391397 (Why is no real title available?)
• scientific article; zbMATH DE number 6437647 (Why is no real title available?)
• 10.1162/153244303321897690
• A semiparametric covariance estimator immune to arbitrary signal drift
• An error bound for L₁-norm support vector machine coefficients in ultra-high dimension
• Essentials of Tropical Combinatorics
• Estimating Spiking Irregularities Under Changing Environments
• Foundations of machine learning
• Model-based classification of radar images
• On the sparseness of 1-norm support vector machines
• Support-vector networks
• Tropical halfspaces
• Tropical principal component analysis and its application to phylogenetics
• VC theory of large margin multi-category classifiers

Cited in

(6)

• Tropical reproducing kernels and optimization
• An invitation to tropical Alexandrov curvature
• Tropical support vector machine and its applications to phylogenomics
• Maximum inscribed and minimum enclosing tropical balls of tropical polytopes and applications to volume estimation and uniform sampling
• Tropical logistic regression model on space of phylogenetic trees
• Tropical gradient descent

This page was built for publication: Tropical Support Vector Machines: Evaluations and Extension to Function Spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6359200)