On the optimality of the max-depth and max-rank classifiers for spherical data

Kód výsledku v IS VaVaI

RIV/61989592:15310/20:73605281 - isvavai.cz

Výsledek na webu

https://link.springer.com/article/10.21136/AM.2020.0331-19

DOI - Digital Object Identifier

10.21136/AM.2020.0331-19

Jazyk výsledku

angličtina

Název v původním jazyce

On the optimality of the max-depth and max-rank classifiers for spherical data

Popis výsledku v původním jazyce

The main goal of supervised learning is to construct a function from labeled training data which assigns arbitrary new data points to one of the labels. Classification tasks may be solved by using some measures of data point centrality with respect to the labeled groups considered. Such a measure of centrality is called data depth. In this paper, we investigate conditions under which depth-based classifiers for directional data are optimal. We show that such classifiers are equivalent to the Bayes (optimal) classifier when the considered distributions are rotationally symmetric, unimodal, differ only in location and have equal priors. The necessity of such assumptions is also discussed.

Název v anglickém jazyce

On the optimality of the max-depth and max-rank classifiers for spherical data

Popis výsledku anglicky

The main goal of supervised learning is to construct a function from labeled training data which assigns arbitrary new data points to one of the labels. Classification tasks may be solved by using some measures of data point centrality with respect to the labeled groups considered. Such a measure of centrality is called data depth. In this paper, we investigate conditions under which depth-based classifiers for directional data are optimal. We show that such classifiers are equivalent to the Bayes (optimal) classifier when the considered distributions are rotationally symmetric, unimodal, differ only in location and have equal priors. The necessity of such assumptions is also discussed.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

—

Návaznosti

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Applications of Mathematics

ISSN

0862-7940

e-ISSN

—

Svazek periodika

65

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

12

Strana od-do

331-342

Kód UT WoS článku

000544260100009

EID výsledku v databázi Scopus

2-s2.0-85087051786