Skip to yearly menu bar Skip to main content


Poster

Position: Why We Must Rethink Empirical Research in Machine Learning

Moritz Herrmann · F. Julian D. Lange · Katharina Eggensperger · Giuseppe Casalicchio · Marcel Wever · Matthias Feurer · David Rügamer · Eyke Hüllermeier · Anne-Laure Boulesteix · Bernd Bischl

Hall C 4-9 #2201
[ ] [ Paper PDF ]
[ Poster
Wed 24 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

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.

Chat is not available.