Fact-free learning
Open accessAbstract
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.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Cites
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · see citing works
(1979) · Cited by 43,841 · see citing works
A BEHAVIORAL MODEL OF RATIONAL CHOICE
Simon, H. A. (1955) · The Quarterly Journal of Economics · doi:10.2307/1884852 · Cited by 15,877 · see citing works
Mallows, C. L. (1995) · Technometrics · doi:10.1080/00401706.1995.10484370 · Cited by 2,083 · see citing works
Mallows, C. L. (1973) · Technometrics · doi:10.2307/1267380 · Cited by 1,978 · see citing works
Normative and Structural Causes of Democratic Peace, 1946–1986
Maoz, Z., & Russett, B. M. (1993) · American Political Science Review · doi:10.2307/2938740 · Cited by 1,536 · see citing works
On the hardness of approximating minimization problems
Lund, C., & Yannakakis, M. (1994) · Journal of the ACM · doi:10.1145/185675.306789 · Cited by 896 · see citing works
A Representation Theorem for "Preference for Flexibility"
Kreps, D. M. (1979) · Econometrica · doi:10.2307/1910406 · Cited by 780 · see citing works
Rational Expectations Equilibria, Learning, and Model Specification
Bray, M., & Savin, N. E. (1986) · Econometrica · doi:10.2307/1912325 · Cited by 380 · see citing works
A Theory of Case-Based Decisions
Gilboa, I., & Schmeidler, D. (2001) · Cambridge University Press eBooks · doi:10.1017/cbo9780511493539 · Cited by 375 · see citing works
Self-citationBehavioral Equilibrium in Economies with Adverse Selection
Esponda, I. (2008) · American Economic Review · doi:10.1257/aer.98.4.1269 · Cited by 170 · see citing works
Incomplete Written Contracts: Undescribable States of Nature
Anderlini, L., & Felli, L. (1994) · The Quarterly Journal of Economics · doi:10.2307/2118357 · Cited by 168 · see citing works
Recent developments in modeling unforeseen contingencies
Dekel, E., Lipman, B. L., & Rustichini, A. (1998) · European Economic Review · doi:10.1016/s0014-2921(97)00114-1 · Cited by 118 · see citing works
Skaperdas, S., & Vaidya, S. (2009) · Economic Theory · doi:10.1007/s00199-009-0497-2 · Cited by 68 · see citing works
Choice Shifts in Groups: A Decision-Theoretic Basis
Eliaz, K., Ray, D., & Razin, R. (2006) · American Economic Review · doi:10.1257/aer.96.4.1321 · Cited by 61 · see citing works
A Unique Subjective State Space for Unforeseen ContingenciesPreprint
Dekel, E. (1997) · RePEc: Research Papers in Economics · Cited by 45 · see citing works
Aragonès, E., Gilboa, I., Postlewaite, A., et al. (2001) · Cited by 14 · see citing works
Self-citationProbabilistic representation of complexity
Al‐Najjar, N. I., Casadesus‐Masanell, R., & Ozdenoren, E. (2003) · Journal of Economic Theory · doi:10.1016/s0022-0531(03)00075-9 · Cited by 13 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Bayesian Brains without Probabilities
Sanborn, A. N., & Chater, N. (2016) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2016.10.003 · Cited by 307 · see citing works
Justifying precautionary policies: Incommensurability and uncertainty
Aldred, J. (2013) · Ecological Economics · doi:10.1016/j.ecolecon.2013.10.006 · Cited by 36 · see citing works
- Authors
- Aragones, E., Gilboa, I., Postlewaite, A., & Schmeidler, D.
- Affiliations
- Institut d'Analisi Economica, CSIC, Campus UAB, 08193 Bellaterra, Spain 08193.
- Tel Aviv University (IL)
- University of Pennsylvania (US)
- ORCID
- Gilboa, Itzhak
- Venue
- American Economic Review
- Publisher
- American Economic Association
- Published
- 2005-11-01
- Volume
- 95
- Issue
- 5
- Pages
- 1355-1368
- ISSN
- 0002-8282 (ISSN-L)
- OpenAlex
- W3122734808
- Cited by
- 123
- References
- 18
- Citations by year
- 2026: 4 · 2025: 3 · 2024: 3 · 2023: 5 · 2022: 1 · 2021: 10 · 2020: 7 · 2019: 5 · 2018: 4 · 2017: 3 · 2016: 7 · 2015: 2 · 2014: 5 · 2013: 6 · 2012: 5
- FWCI
- 9.52
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- other-oa
- Locations
- American Economic Review (publishedVersion)
- HAL (submittedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DIGITAL.CSIC (Spanish National Research Council (CSIC)) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Keywords
- computational complexity, knowledge base, R-squared, feature selection, computational hardness, knowledge acquisition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
