PhilSci Archive

A New Solution to the Puzzle of Simplicity

Kelly, Kevin (2006) A New Solution to the Puzzle of Simplicity. In: UNSPECIFIED.

[img]
Preview
PDF
psa2006b.pdf

Download (167kB)

Abstract

Explaining the connection, if any, between simplicity and truth is among the deepest problems facing the philosophy of science, statistics, and machine learning. Say that an efficient truth-finding method minimizes worst-case costs en route to converging to the true answer to a theory choice problem. Let the costs considered include the number of times a false answer is selected, the number of times opinion is reversed, and the times at which the reversals occur. It is demonstrated that (1)always choosing the simplest theory compatible with experience and (2) hanging onto it while it remains simplest is both necessary and sufficient for efficiency.


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

Item Type: Conference or Workshop Item (UNSPECIFIED)
Creators:
CreatorsEmailORCID
Kelly, Kevin
Keywords: induction, ockham, simplicity, goodman, truth, convergence, akaike, formal learning theory, model selection, theory choice
Subjects: General Issues > Confirmation/Induction
Depositing User: Kevin Kelly
Date Deposited: 15 Oct 2006
Last Modified: 07 Oct 2010 15:14
Item ID: 2984
Subjects: General Issues > Confirmation/Induction
Date: 2006
URI: https://philsci-archive.pitt.edu/id/eprint/2984

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item