Saved in:
Bibliographic Details
Main Authors: Herrmann, Moritz, Lange, F. Julian D., Eggensperger, Katharina, Casalicchio, Giuseppe, Wever, Marcel, Feurer, Matthias, Rügamer, David, Hüllermeier, Eyke, Boulesteix, Anne-Laure, Bischl, Bernd
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.02200
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914810986233856
author Herrmann, Moritz
Lange, F. Julian D.
Eggensperger, Katharina
Casalicchio, Giuseppe
Wever, Marcel
Feurer, Matthias
Rügamer, David
Hüllermeier, Eyke
Boulesteix, Anne-Laure
Bischl, Bernd
author_facet Herrmann, Moritz
Lange, F. Julian D.
Eggensperger, Katharina
Casalicchio, Giuseppe
Wever, Marcel
Feurer, Matthias
Rügamer, David
Hüllermeier, Eyke
Boulesteix, Anne-Laure
Bischl, Bernd
contents We warn against a common but incomplete understanding of empirical research in machine learning that leads to non-replicable results, makes findings unreliable, and threatens to undermine progress in the field. To overcome this alarming situation, we call for more awareness of the plurality of ways of gaining knowledge experimentally but also of some epistemic limitations. In particular, we argue most current empirical machine learning research is fashioned as confirmatory research while it should rather be considered exploratory.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02200
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Position: Why We Must Rethink Empirical Research in Machine Learning
Herrmann, Moritz
Lange, F. Julian D.
Eggensperger, Katharina
Casalicchio, Giuseppe
Wever, Marcel
Feurer, Matthias
Rügamer, David
Hüllermeier, Eyke
Boulesteix, Anne-Laure
Bischl, Bernd
Machine Learning
We warn against a common but incomplete understanding of empirical research in machine learning that leads to non-replicable results, makes findings unreliable, and threatens to undermine progress in the field. To overcome this alarming situation, we call for more awareness of the plurality of ways of gaining knowledge experimentally but also of some epistemic limitations. In particular, we argue most current empirical machine learning research is fashioned as confirmatory research while it should rather be considered exploratory.
title Position: Why We Must Rethink Empirical Research in Machine Learning
topic Machine Learning
url https://arxiv.org/abs/2405.02200