Sterkenburg, Tom F. and Grünwald, Peter D. (2021) The No-Free-Lunch Theorems of Supervised Learning. Synthese.

Preview

Text enefel.pdf - Accepted Version Download (659kB) | Preview

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.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Published Article or Volume
Creators:	Creators Email ORCID Sterkenburg, Tom F. tom.sterkenburg@lmu.de 0000-0002-4860-727X Grünwald, Peter D.
Subjects:	Specific Sciences > Computer Science General Issues > Confirmation/Induction Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User:	Mr Tom Sterkenburg
Date Deposited:	14 Jul 2021 02:25
Last Modified:	14 Jul 2021 02:25
Item ID:	19300
Journal or Publication Title:	Synthese
DOI or Unique Handle:	10.1007/s11229-021-03233-1
Subjects:	Specific Sciences > Computer Science General Issues > Confirmation/Induction Specific Sciences > Artificial Intelligence > Machine Learning
Date:	2021
URI:	https://philsci-archive.pitt.edu/id/eprint/19300

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Altmetric.com

Actions (login required)

View Item