The no-free-lunch theorems of supervised learning

Sterkenburg, Tom F. and Grunwald, Peter D. (2021): The no-free-lunch theorems of supervised learning. In: Synthese, Vol. 199, No. 3-4: pp. 9979-10015

Abstract

The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are better than others? Drawing parallels to the philosophy of induction, we point out that the no-free-lunch results presuppose a conception of learning algorithms as purely data-driven. On this conception, every algorithm must have an inherent inductive bias, that wants justification. We argue that many standard learning algorithms should rather be understood as model-dependent: in each application they also require for input a model, representing a bias. Generic algorithms themselves, they can be given a model-relative justification.

• Item Type: Journal article
• Faculties: Philosophy, Philosophy of Science and Religious Science
• Subjects: 100 Philosophy and Psychology > 100 Philosophy
• ISSN: 0039-7857
• Language: English