A New Solution to the Puzzle of Simplicity

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 anefficienttruth finding method minimizes worst case costs en route to converging to the true answer to a theory choice problem....

Full description

Saved in:
Bibliographic Details
Published inPhilosophy of science Vol. 74; no. 5; pp. 561 - 573
Main Author Kelly, Kevin T.
Format Journal Article Conference Proceeding
LanguageEnglish
Published Chicago, IL The University of Chicago Press 01.12.2007
University of Chicago Press
Cambridge University Press
Subjects
A priori knowledge
Aesthetic simplicity
Artificial intelligence
Empiricism
Epistemology. Philosophy of science. Theory of knowledge
Evolutionary theories
Inference
Information theory
Philosophy
Philosophy of science
Polynomials
Sample size
Statistics
Theory
Truth
Science philosophy
Online AccessGet full text

Cover

More Information
Summary: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 anefficienttruth 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.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0031-8248
1539-767X
DOI:10.1086/525604