Fact-Free Learning

Itzhak Gilboa (1) , Enriqueta Aragones , Andrew Postlewaite , David Schmeidler

1 TAU - Tel Aviv University

People may be surprised by noticing 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 database, finding a small set of variables that obtain a certain value of R^2 is 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.

Mots clés: Computational complexity; Linear regression; Rule-based reasoning

Domaines: Economie et sciences de la décision

Itzhak Gilboa, Enriqueta Aragones, Andrew Postlewaite, David Schmeidler. Fact-Free Learning. American Economic Review, 2005, Vol.95, pp.1355-1368. ⟨10.1257/000282805775014308⟩. ⟨hal-00481243⟩