PhilSci Archive

Theory Choice, Non-epistemic Values, and Machine Learning

Dotan, Ravit (2020) Theory Choice, Non-epistemic Values, and Machine Learning. [Preprint]

[img]
Preview
Text
Dotan-Theory choice and ML.pdf - Accepted Version

Download (495kB) | Preview

Abstract

I use a theorem from machine learning, called the “No Free Lunch” theorem (NFL) to support the claim that non-epistemic values are essential to theory choice. I argue that NFL entails that predictive accuracy is insufficient to favor a given theory over others, and that NFL challenges our ability to give a purely epistemic justification for using other traditional epistemic virtues in theory choice. In addition, I argue that the natural way to overcome NFL’s challenge is to use non-epistemic values. If my argument holds, non-epistemic values are entangled in theory choice regardless of human limitations and regardless of the subject matter. Thereby, my argument overcomes objections to the main lines of argument revealing the role of values in theory choice. At the end of the paper, I argue that, contrary to common conception, the epistemic challenge arising from NFL is distinct from Hume’s problem of induction and other forms of underdetermination


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Dotan, Ravitravit.dotan@berkeley.edu0000-0002-9646-8315
Keywords: Theory choice; Epistemic values; Machine learning; the No Free Lunch theorem
Subjects: Specific Sciences > Artificial Intelligence
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Theory Change
General Issues > Values In Science
Depositing User: Ravit Dotan
Date Deposited: 08 Aug 2020 02:25
Last Modified: 08 Aug 2020 02:25
Item ID: 17707
Subjects: Specific Sciences > Artificial Intelligence
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Theory Change
General Issues > Values In Science
Date: 2020
URI: https://philsci-archive.pitt.edu/id/eprint/17707

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item