Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published November 2020 | Published
Journal Article Open

On the falsifiability and learnability of decision theories


We study the degree of falsifiability of theories of choice. A theory is easy to falsify if relatively small datasets are enough to guarantee that the theory can be falsified: the VC dimension of a theory is the largest sample size for which the theory is "never falsifiable." VC dimension is motivated strategically. We consider a model with a strategic proponent of a theory, and a skeptical consumer, or user, of theories. The former presents experimental evidence in favor of the theory, and the latter may doubt whether the experiment could ever have falsified the theory. We focus on decision-making under uncertainty, considering the central models of Expected Utility, Choquet Expected Utility and Max-min Expected Utility models. We show that Expected Utility has VC dimension that grows linearly with the number of states while that of Choquet Expected Utility grows exponentially. The Max-min Expected Utility model has infinite VC dimension when there are at least three states of the world. In consequence, Expected Utility is easily falsified, while the more flexible Choquet and Max-min Expected Utility are hard to falsify. Finally, as VC dimension and statistical estimation are related, we study the implications of our results for machine learning approaches to preference recovery.

Additional Information

© 2020 The Authors. Licensed under the Creative Commons Attribution-NonCommercial License 4.0. Co-editor Ran Spiegler handled this manuscript. Manuscript received 11 September, 2018; final version accepted 22 February, 2020; available online 27 February, 2020. We thank Fabio Maccheroni, Burkhard Schipper, and Adam Wierman for useful comments on a previous draft. We are also very grateful to the three anonymous referees for their suggestions and feedback. Echenique acknowledges NSF funding through Grants SES-1558757 and CNS-1518941, as well as the Linde Institute of Economic and Management Science at Caltech.

Attached Files

Published - TE3438.pdf


Files (206.2 kB)
Name Size Download all
206.2 kB Preview Download

Additional details

August 20, 2023
October 23, 2023