Depth functions for partial orders with a descriptive analysis of machine learning algorithms

LANCASTER UNIVERSITY LEIPZIG

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Depth functions for partial orders with a descriptive analysis of machine learning algorithms. / Blocher, Hannah; Schollmeyer, Georg; Jansen, Christoph et al.
Proceedings of the Thirteenth International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2023). PMLR, 2023. p. 59-71 (PMLR; Vol. 215).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Blocher, H, Schollmeyer, G, Jansen, C & Nalenz, M 2023, Depth functions for partial orders with a descriptive analysis of machine learning algorithms. in Proceedings of the Thirteenth International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2023). PMLR, vol. 215, PMLR, pp. 59-71. <https://proceedings.mlr.press/v215/blocher23a.html>

APA

Blocher, H., Schollmeyer, G., Jansen, C., & Nalenz, M. (2023). Depth functions for partial orders with a descriptive analysis of machine learning algorithms. In Proceedings of the Thirteenth International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2023) (pp. 59-71). (PMLR; Vol. 215). PMLR. https://proceedings.mlr.press/v215/blocher23a.html

Vancouver

Blocher H, Schollmeyer G, Jansen C, Nalenz M. Depth functions for partial orders with a descriptive analysis of machine learning algorithms. In Proceedings of the Thirteenth International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2023). PMLR. 2023. p. 59-71. (PMLR).

Author

Blocher, Hannah ; Schollmeyer, Georg ; Jansen, Christoph et al. / Depth functions for partial orders with a descriptive analysis of machine learning algorithms. Proceedings of the Thirteenth International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2023). PMLR, 2023. pp. 59-71 (PMLR).

Bibtex

@inproceedings{bd505d3667214701be9101aff4b41024,

title = "Depth functions for partial orders with a descriptive analysis of machine learning algorithms",

abstract = "We propose a framework for descriptively analyzing sets of partial orders based on the concept of depth functions. Despite intensive studies of depth functions in linear and metric spaces, there is very little discussion on depth functions for non-standard data types such as partial orders. We introduce an adaptation of the well-known simplicial depth to the set of all partial orders, the union-free generic (ufg) depth. Moreover, we utilize our ufg depth for a comparison of machine learning algorithms based on multidimensional performance measures. Concretely, we analyze the distribution of different classifier performances over a sample of standard benchmark data sets. Our results promisingly demonstrate that our approach differs substantially from existing benchmarking approaches and, therefore, adds a new perspective to the vivid debate on the comparison of classifiers.",

author = "Hannah Blocher and Georg Schollmeyer and Christoph Jansen and Malte Nalenz",

year = "2023",

month = jul,

day = "14",

language = "English",

series = "PMLR",

publisher = "PMLR",

pages = "59--71",

booktitle = "Proceedings of the Thirteenth International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2023)",

}

RIS

TY - GEN

T1 - Depth functions for partial orders with a descriptive analysis of machine learning algorithms

AU - Blocher, Hannah

AU - Schollmeyer, Georg

AU - Jansen, Christoph

AU - Nalenz, Malte

PY - 2023/7/14

Y1 - 2023/7/14

N2 - We propose a framework for descriptively analyzing sets of partial orders based on the concept of depth functions. Despite intensive studies of depth functions in linear and metric spaces, there is very little discussion on depth functions for non-standard data types such as partial orders. We introduce an adaptation of the well-known simplicial depth to the set of all partial orders, the union-free generic (ufg) depth. Moreover, we utilize our ufg depth for a comparison of machine learning algorithms based on multidimensional performance measures. Concretely, we analyze the distribution of different classifier performances over a sample of standard benchmark data sets. Our results promisingly demonstrate that our approach differs substantially from existing benchmarking approaches and, therefore, adds a new perspective to the vivid debate on the comparison of classifiers.

AB - We propose a framework for descriptively analyzing sets of partial orders based on the concept of depth functions. Despite intensive studies of depth functions in linear and metric spaces, there is very little discussion on depth functions for non-standard data types such as partial orders. We introduce an adaptation of the well-known simplicial depth to the set of all partial orders, the union-free generic (ufg) depth. Moreover, we utilize our ufg depth for a comparison of machine learning algorithms based on multidimensional performance measures. Concretely, we analyze the distribution of different classifier performances over a sample of standard benchmark data sets. Our results promisingly demonstrate that our approach differs substantially from existing benchmarking approaches and, therefore, adds a new perspective to the vivid debate on the comparison of classifiers.

M3 - Conference contribution/Paper

T3 - PMLR

SP - 59

EP - 71

BT - Proceedings of the Thirteenth International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2023)

PB - PMLR

ER -

Research

Links