Fact-Free Learning
- 1 November 2005
- journal article
- Published by American Economic Association in American Economic Review
- Vol. 95 (5) , 1355-1368
- https://doi.org/10.1257/000282805775014308
Abstract
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.Keywords
This publication has 8 references indexed in Scilit:
- Probabilistic representation of complexityJournal of Economic Theory, 2003
- Recent developments in modeling unforeseen contingenciesEuropean Economic Review, 1998
- Regression Shrinkage and Selection Via the LassoJournal of the Royal Statistical Society Series B: Statistical Methodology, 1996
- Incomplete Written Contracts: Undescribable States of NatureThe Quarterly Journal of Economics, 1994
- On the hardness of approximating minimization problemsJournal of the ACM, 1994
- Normative and Structural Causes of Democratic Peace, 1946–1986American Political Science Review, 1993
- Rational Expectations Equilibria, Learning, and Model SpecificationEconometrica, 1986
- A Representation Theorem for "Preference for Flexibility"Econometrica, 1979