Accuracy vs. Simplicity: A Complex Trade-Off
AbstractInductive learning aims at finding general rules that hold true in a database. Targeted learning seeks rules for the predictions of the value of a variable based on the values of others, as in the case of linear or non-parametric regression analysis. Non-targeted learning finds regularities without a specific prediction goal. We model the product of non-targeted learning as rules that state that a certain phenomenon never happens, or that certain conditions necessitate another. For all types of rules, there is a trade-off between the rule's accuracy and its simplicity. Thus rule selection can be viewed as a choice problem, among pairs of degree of accuracy and degree of complexity. However, one cannot in general tell what is the feasible set in the accuracy-complexity space. Formally, we show that finding out whether a point belongs to this set is computationally hard. In particular, in the context of linear regression, finding a small set of variables that obtain a certain value of R2 is computationally hard. Computational complexity may explain why a person is not always aware of rules that, if asked, she would find valid. This, in turn, may explain why one can change other people's minds (opinions, beliefs) without providing new information.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by David K. Levine in its series Levine's Working Paper Archive with number 506439000000000185.
Date of creation: 24 Jan 2003
Date of revision:
Contact details of provider:
Web page: http://www.dklevine.com/
Other versions of this item:
- D83 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Search, Learning, and Information
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Dekel, Eddie & Lipman, Barton L. & Rustichini, Aldo, 1998. "Recent developments in modeling unforeseen contingencies," European Economic Review, Elsevier, vol. 42(3-5), pages 523-542, May.
- Gilboa, I. & Schmeidler, D., 1999.
"Cognitive Foundations of Probability,"
30-99, Tel Aviv.
- Gilboa,Itzhak & Schmeidler,David, 2001.
"A Theory of Case-Based Decisions,"
Cambridge University Press, number 9780521003117, April.
- Enriqueta Aragonès & Itzhak Gilboa & Andrew Postlewaite & David Schmeidler, 2013.
"Rhetoric and Analogies,"
706, Barcelona Graduate School of Economics.
- Aragones, E. & Gilboa, I. & Postlewaite, A. & Schmeidler, D., 2001. "Rhetoric and Analogies," Papers 2001-15, Tel Aviv.
- Enriqueta Aragones & Itzhak Gilboa & Andrew Postlewaite & David Schmeidler, 2013. "Rhetoric and Analogies," UFAE and IAE Working Papers 932.13, Unitat de Fonaments de l'Anàlisi Econòmica (UAB) and Institut d'Anàlisi Econòmica (CSIC).
- Enriqueta Aragones & Itzhak Gilboa & Andrew Postlewaite & David Schmeidler, 2013. "Rhetoric and Analogies," PIER Working Paper Archive 13-039, Penn Institute for Economic Research, Department of Economics, University of Pennsylvania.
- Itzhak Gilboa & David Schmeidler, 2001.
"Inductive Inference: An Axiomatic Approach,"
Cowles Foundation Discussion Papers
1339, Cowles Foundation for Research in Economics, Yale University.
- Itzhak Gilboa & David Schmeidler, 2002. "Inductive Inference: An Axiomatic Approach," Levine's Working Paper Archive 391749000000000544, David K. Levine.
- Gilboa, I. & Schmeidler, D., 1999. "Inductive Inference: an Axiomatic Approach," Papers 29-99, Tel Aviv.
- Gilboa, I. & Schmeidler, D., 2001. "Inductive Inference: An Axiomatic Approach," Papers 2001-19, Tel Aviv.
- Itzhak Gilboa & David Schmeidler, 2002. "Inductive Inference: An Axiomatic Approach," NajEcon Working Paper Reviews 391749000000000544, www.najecon.org.
- Rafael LaPorta & Florencio Lopez-de-Silanes & Andrei Shleifer & Robert Vishny, .
"The Quality of Government,"
19452, Harvard University OpenScholar.
- Rafael La Porta & Florencio Lopez-de-Silanes & Andrei Shleifer & Robert Vishny, 1998. "The Quality of Goverment," NBER Working Papers 6727, National Bureau of Economic Research, Inc.
- Andrei Shleifer & Robert W. Vishny, 1998. "The Quality of Government," Harvard Institute of Economic Research Working Papers 1847, Harvard - Institute of Economic Research.
- Bray, Margaret M & Savin, Nathan E, 1986. "Rational Expectations Equilibria, Learning, and Model Specification," Econometrica, Econometric Society, vol. 54(5), pages 1129-60, September.
- Itzhak Gilboa, 1993. "Hempel, Good and Bayes," Discussion Papers 1045, Northwestern University, Center for Mathematical Studies in Economics and Management Science.
- Anderlini, L. & Felli, L., 1993.
"Incomplete Written Contracts: Undescribable States of Nature,"
183, Cambridge - Risk, Information & Quantity Signals.
- Anderlini, Luca & Felli, Leonardo, 1994. "Incomplete Written Contracts: Undescribable States of Nature," The Quarterly Journal of Economics, MIT Press, vol. 109(4), pages 1085-1124, November.
- Kreps, David M, 1979. "A Representation Theorem for "Preference for Flexibility"," Econometrica, Econometric Society, vol. 47(3), pages 565-77, May.
- Dekel, Eddie & Lipman, Barton L & Rustichini, Aldo, 2001.
"Representing Preferences with a Unique Subjective State Space,"
Econometric Society, vol. 69(4), pages 891-934, July.
- Eddie Dekel, 1997. "A Unique Subjective State Space for Unforeseen Contingencies," Discussion Papers 1202, Northwestern University, Center for Mathematical Studies in Economics and Management Science.
- Gabaix, Xavier & Laibson, David Isaac & Moloche, Guillermo & Stephen, Weinberg, 2003. "The allocation of attention: theory and evidence," MPRA Paper 47339, University Library of Munich, Germany.
- Xavier Gabaix & David Laibson & Guillermo Moloche & Stephen Weinberg, 2005. "Information Acquisition: Experimental Analysis of a Boundedly Rational Model," Levine's Bibliography 666156000000000480, UCLA Department of Economics.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (David K. Levine).
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
If references are entirely missing, you can add them using this form.
If the full references list an item that is present in RePEc, but the system did not link to it, you can help with this form.
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your profile, as there may be some citations waiting for confirmation.
Please note that corrections may take a couple of weeks to filter through the various RePEc services.