35 Pages Posted: 24 Nov 2004
Date Written: October 2004
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.
Notes: An updated version of this abstract can be found at: http://ssrn.com/abstract=643545
Keywords: Computational complexity, Linear regression, Rule-based reasoning
JEL Classification: C8, D8
Suggested Citation: Suggested Citation
Aragones, Enriqueta and Gilboa, Itzhak and Postlewaite, Andrew and Schmeidler, David, Fact-Free Learning (October 2004). PIER Working Paper No. 03-023; Cowles Foundation Discussion Paper No. 1491. Available at SSRN: https://ssrn.com/abstract=460203