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....
Saved in:
Published in | Philosophy of science Vol. 74; no. 5; pp. 561 - 573 |
---|---|
Main Author | |
Format | Journal Article Conference Proceeding |
Language | English |
Published |
Chicago, IL
The University of Chicago Press
01.12.2007
University of Chicago Press Cambridge University Press |
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |