Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Machine learning for evaluating and improving theories

Machine learning for evaluating and improving theories We summarize our recent work that uses machine learning techniques as a complement to theoretical modeling, rather than a substitute for it. The key concepts are those of the completeness and restrictiveness of a model. A theory's completeness is how much it improves predictions over a naive baseline, relative to how much improvement is possible. When a theory is relatively incomplete, machine learning algorithms can help reveal regularities that the theory doesn't capture, and thus lead to the construction of theories that make more accurate predictions. Restrictiveness measures a theory's ability to match arbitrary hypothetical data: A very unrestrictive theory will be complete on almost any data, so the fact that it is complete on the actual data is not very instructive. We algorithmically quantify restrictiveness by measuring how well the theory approximates randomly generated behaviors. Finally, we propose "algorithmic experimental design" as a method to help select which experiments to run. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM SIGecom Exchanges Association for Computing Machinery

Machine learning for evaluating and improving theories

Fudenberg, Drew; Liang, Annie
ACM SIGecom Exchanges , Volume 18 (1): 8 – Dec 2, 2020
Download PDF
8 pages

Loading next page...
 
/lp/association-for-computing-machinery/machine-learning-for-evaluating-and-improving-theories-mj0ZxTI6X0

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2020 Copyright is held by the owner/author(s)
ISSN
1551-9031
eISSN
1551-9031
DOI
10.1145/3440959.3440962
Publisher site
See Article on Publisher Site

Abstract

We summarize our recent work that uses machine learning techniques as a complement to theoretical modeling, rather than a substitute for it. The key concepts are those of the completeness and restrictiveness of a model. A theory's completeness is how much it improves predictions over a naive baseline, relative to how much improvement is possible. When a theory is relatively incomplete, machine learning algorithms can help reveal regularities that the theory doesn't capture, and thus lead to the construction of theories that make more accurate predictions. Restrictiveness measures a theory's ability to match arbitrary hypothetical data: A very unrestrictive theory will be complete on almost any data, so the fact that it is complete on the actual data is not very instructive. We algorithmically quantify restrictiveness by measuring how well the theory approximates randomly generated behaviors. Finally, we propose "algorithmic experimental design" as a method to help select which experiments to run.

Journal

ACM SIGecom Exchanges – Association for Computing Machinery

Published: Dec 2, 2020

Keywords: economic theory

References

  • Risk and rationality: Uncovering heterogeneity in probability distortion
    Bruhin, ; A., ; Fehr-Duda, ; H., ; Epper, ; T.,
  • A cognitive hierarchy model of games
    Camerer, ; F., C.; Ho, ; T.-H., ; Chong, ; J.-K.,
  • Quantifying the restrictiveness of theories
    Fudenberg, ; D., ; Gao, ; W., ; Liang, ; A.,
  • Measuring the com- pleteness of theories
    Fudenberg, ; D., ; Kleinberg, ; J., ; Liang, ; A., ; Mullainathan, ; S.,
  • Predicting and understanding initial play
    Fudenberg, ; D., ; Liang, ; A.,
  • Expression theory and the preference reversal phenomena
    Goldstein, ; M., W.; Einhorn, ; J., H.
  • Generative adversarial networks
    Goodfellow, ; I., ; Pouget-Abadie, ; J., ; Mirza, ; M., ; Xu, ; B., ; Warde-Farley, ; D., ; Ozair, ; S., ; Courville, ; A., ; Bengio, ; Y.,
  • Adversarial machine learning
    Huang, ; L., ; Joseph, ; D., A.; Nelson, ; B., ; Rubinstein, ; B., ; Tygar, ; J.,
  • The influence of probability on risky choice: A parametric examination
    Lattimore, ; K., P.; Baker, ; R., J.; Witte, ; D., A.
  • Unraveling in guessing games: An experimental study
    Nagel, ; R.,
  • Experimental evidence on players' models of other players
    Stahl, ; O., D.; Wilson, ; W., P.
  • On players' models of other players: Theory and exper- imental evidence
    Stahl, ; O., D.; Wilson, ; W., P.
  • Level-0 meta-models for predicting human behavior in games
    Wright, ; R., J.; Leyton-Brown, ; K.,