Position Paper: Rethinking Empirical Research in Machine Learning: Addressing Epistemic and Methodological Challenges of Experimentation

arXiv:2405.02200v1 Announce Type: new
Abstract: We warn against a common but incomplete understanding of empirical research in machine learning (ML) 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 ML research is fashioned as confirmatory research while it should rather be …

abstract arxiv call challenges cs.lg experimentation leads machine machine learning paper progress research results stat.ml type undermine understanding