Information-constrained coordination of economic behavior
Open accessAbstract
We analyze a coordination game with information-constrained players.The players' actions are based on a noisy compressed representation of the game's payoffs in a particular case, where the compressed representation is a latent state learned by a variational autoencoder (VAE).Our generalized VAE is optimized to trade off the average payoff obtained over a distribution of possible games against a measure of the congruence between the agent's internal model and the statistics of its environment.We apply our model to the coordination game in the experiment of Frydman and Nunnari (2023), and show that it offers an explanation for two salient features of the experimental evidence: both the relatively continuous variation in the players' action probabilities with changes in the game payoffs, and the dependence of the degree of stochasticity of players' choices on the range of game payoffs encountered on different trials.Our approach also provides an account of the way in which play should gradually adjust to a change in the distribution of game payoffs that are encountered, offering an explanation for the historydependent play documented by Arifovic et al. (2013).
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The flexibility of VIB has supported applications of Information Bottleneck methods across disciplines, including economics and modeling of human intelligence.
“The flexibility of VIB has in turn supported applications of Information Bottleneck methods across disciplines, including economics (Aridor et al., 2024) and modeling of human intelligence (Malloy, 2022).”
From Towards Human-Like Emergent Communication via Utility, Informativeness, and Complexity (2025) · cites this paper as Aridor et al., 2024
The Introduction describes an economic decision-making model built on a variational autoencoder, and §2.2 relates its training objective to mutual information. This supports the economics application, but the paper does not identify its approach as VIB or say that VIB’s flexibility enabled it. The separate claim about modeling human intelligence is attributed to Malloy (2022), not to this source. (LLM, conf=0.86)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Towards Human-Agent Communication via the Information Bottleneck PrinciplePreprint
Tucker, M., Shah, J., Lévy, R., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.00088 · Cited by 8 · see citing works
Flagged first, then by citations
Research works printed but not linked: 15
- Alemi, A., B. Poole, I. Fischer, J. Dillon, R. A. Saurous, and K. Murphy (2018). Fixing a broken elbo. In International Conference on Machine Learning, pp. 159-168.
- Arifovic, J. and J. H. Jiang (2019). Strategic uncertainty and the power of extrinsic signals - evidence from an experimental study of bank runs. Journal of Economic Behavior and Organi- zation 167, 1-17.
- Arifovic, J., J. H. Jiang, and Y. Xu (2013). Experimental evidence of bank runs as pure coordination failures. Journal of Economic Dynamics and Control 37(12), 2446-2465.
- Bowman, S., L. Vilnis, O. Vinyals, A. Dai, R. Jozefowicz, and S. Bengio (2016). Generating sentences from a continuous space. In Proceedings of The 20th SIGNLL Conference on Compu- tational Natural Language Learning, pp. 10-21.
- Chen, X., D. P. Kingma, T. Salimans, Y. Duan, P. Dhariwal, J. Schulman, I. Sutskever, and P. Abbeel (2017). Variational lossy autoencoder. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
- Goeree, J. K., C. A. Holt, and T. R. Palfrey (2016). Quantal response equilibrium: A stochastic theory of games. Princeton University Press.
- Heinemann, F., R. Nagel, and P. Ockenfels (2004). The theory of global games on test: experi- mental analysis of coordination games with public and private information. Econometrica 72(5), 1583-1599.
- Heinemann, F., R. Nagel, and P. Ockenfels (2009). Measuring strategic uncertainty in coordination games. Review of Economic Studies 76(1), 181-221.
- Kingma, D. P. and M. Welling (2014). Auto-encoding variational bayes. In Y. Bengio and Y. Le- Cun (Eds.), 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings.
- Kingma, D. P., M. Welling, et al. (2019). An introduction to variational autoencoders. Foundations and Trends® in Machine Learning 12(4), 307-392.
- Mauersberger, F. (2022). Thompson sampling: A behavioral model of expectation formation for economics. Available at SSRN 4128376.
- Morris, S. and H. S. Shin (2003). Global games: Theory and applications. In M. Dewatripont, L. Hansen, and S. Turnovsky (Eds.), Advances in Economics and Econometrics: Eighth World Congress, pp. 56-114. Cambridge University Press.
- Sims, C. A. (2003). Implications of rational inattention. Journal of Monetary Economics 50(3), 665-690.
- Woodford, M. (2020). Modeling imprecision in perception, valuation and choice. Annual Review of Economics 12, 579-601.
- Yang, M. (2015). Coordination with flexible information acquisition. Journal of Economic The- ory 158, 721-738.
Cited by
Sorted by citations
Towards Human-Like Emergent Communication via Utility, Informativeness, and Complexity
Tucker, M., Shah, J., Levy, R., & Zaslavsky, N. (2025) · Open Mind · doi:10.1162/opmi_a_00188 · Cited by 2 · see citing works
- Authors
- Aridor, G., Azeredo da Silveira, R., & Woodford, M.
- Affiliations
- Northwestern University (US)
- Columbia University (US)
- Venue
- National Bureau of Economic Research
- Publisher
- National Bureau of Economic Research
- Published
- 2024-02
- OpenAlex
- W4392183550
- Cited by
- 3
- References
- 1
- Citations by year
- 2025: 1 · 2024: 2
- Type
- report
- Language
- en
- Open access
- green
- doi.org
- Locations
- National Bureau of Economic Research (publishedVersion)
- Funders
- Centre National de la Recherche Scientifique (UMR8023)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Game Theory and Applications
- Social Sciences › Safety Research › Experimental Behavioral Economics Studies
- Social Sciences › Decision Sciences › General Decision Sciences › Decision-Making and Behavioral Economics
- Keywords
- coordination games, information constraints, variational autoencoder, internal models, payoff distribution, stochastic choice, economic behavior, game-theoretic learning
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
