Fact-Free Learning

People may be surprised to notice certain regularities that hold in existing knowledge they have had for some time. That is, they may learn without getting new factual information. We argue that this can be partly explained by computational complexity. We show that, given a knowledge base, finding a...

Full description

Saved in:
Bibliographic Details
Published in:The American economic review 2005-12, Vol.95 (5), p.1355-1368
Main Authors: Enriqueta Aragones, Gilboa, Itzhak, Postlewaite, Andrew, Schmeidler, David
Format: Article
Language:English
Subjects:
Approximation
Beliefs
Computer science
domain_shs.eco.eco
Econometrics
Economic agents
Economic analysis
Economic modeling
Economic models
Economic theory
Economics and Finance
Humanities and Social Sciences
Information acquisition
Information economics
Knowledge
Knowledge bases
Learning
Linear regression
Mathematical models
Polynomials
Regression analysis
Statistical methods
Studies
Theory
Variables
War
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:People may be surprised to notice certain regularities that hold in existing knowledge they have had for some time. That is, they may learn without getting new factual information. We argue that this can be partly explained by computational complexity. We show that, given a knowledge base, finding a small set of variables that obtain a certain value of R2is computationally hard, in the sense that this term is used in computer science. We discuss some of the implications of this result and of fact-free learning in general.
ISSN:0002-8282
1944-7981
DOI:10.1257/000282805775014308