IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2102.04594.html
   My bibliography  Save this paper

Rationally Inattentive Utility Maximization for Interpretable Deep Image Classification

Author

Listed:
  • Kunal Pattanayak
  • Vikram Krishnamurthy

Abstract

Are deep convolutional neural networks (CNNs) for image classification explainable by utility maximization with information acquisition costs? We demonstrate that deep CNNs behave equivalently (in terms of necessary and sufficient conditions) to rationally inattentive utility maximizers, a generative model used extensively in economics for human decision making. Our claim is based by extensive experiments on 200 deep CNNs from 5 popular architectures. The parameters of our interpretable model are computed efficiently via convex feasibility algorithms. As an application, we show that our economics-based interpretable model can predict the classification performance of deep CNNs trained with arbitrary parameters with accuracy exceeding 94% . This eliminates the need to re-train the deep CNNs for image classification. The theoretical foundation of our approach lies in Bayesian revealed preference studied in micro-economics. All our results are on GitHub and completely reproducible.

Suggested Citation

  • Kunal Pattanayak & Vikram Krishnamurthy, 2021. "Rationally Inattentive Utility Maximization for Interpretable Deep Image Classification," Papers 2102.04594, arXiv.org, revised Jul 2021.
  • Handle: RePEc:arx:papers:2102.04594
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2102.04594
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Andrew Caplin & Daniel Martin, 2015. "A Testable Theory of Imperfect Perception," Economic Journal, Royal Economic Society, vol. 125(582), pages 184-202, February.
    2. Andrew Caplin & Mark Dean, 2015. "Revealed Preference, Rational Inattention, and Costly Information Acquisition," American Economic Review, American Economic Association, vol. 105(7), pages 2183-2203, July.
    3. Varian, H.R., 1991. "Goodness of Fit for Revealed Preference Tests," Papers 13, Michigan - Center for Research on Economic & Social Theory.
    4. Sims, Christopher A., 2003. "Implications of rational inattention," Journal of Monetary Economics, Elsevier, vol. 50(3), pages 665-690, April.
    5. Sebastian Bach & Alexander Binder & Grégoire Montavon & Frederick Klauschen & Klaus-Robert Müller & Wojciech Samek, 2015. "On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation," PLOS ONE, Public Library of Science, vol. 10(7), pages 1-46, July.
    6. Paul R. Milgrom, 1981. "Good News and Bad News: Representation Theorems and Applications," Bell Journal of Economics, The RAND Corporation, vol. 12(2), pages 380-391, Autumn.
    7. W. E. Diewert, 1973. "Afriat and Revealed Preference Theory," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 40(3), pages 419-425.
    8. repec:hal:pseose:halshs-01155313 is not listed on IDEAS
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Kunal Pattanayak & Vikram Krishnamurthy, 2021. "Unifying Revealed Preference and Revealed Rational Inattention," Papers 2106.14486, arXiv.org, revised Jun 2023.
    2. Naudé, Wim, 2023. "Artificial Intelligence and the Economics of Decision-Making," IZA Discussion Papers 16000, Institute of Labor Economics (IZA).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Brocas, Isabelle & Carrillo, Juan D., 2021. "Value computation and modulation: A neuroeconomic theory of self-control as constrained optimization," Journal of Economic Theory, Elsevier, vol. 198(C).
    2. Cristina Gualdani & Shruti Sinha, 2019. "Identification in discrete choice models with imperfect information," Papers 1911.04529, arXiv.org, revised Dec 2023.
    3. Andrew Caplin & Mark Dean & John Leahy, 2022. "Rationally Inattentive Behavior: Characterizing and Generalizing Shannon Entropy," Journal of Political Economy, University of Chicago Press, vol. 130(6), pages 1676-1715.
    4. Mensch, Jeffrey, 2021. "Rational inattention and the monotone likelihood ratio property," Journal of Economic Theory, Elsevier, vol. 196(C).
    5. Spyros Galanis & Sergei Mikhalishchev, 2024. "Information Aggregation with Costly Information Acquisition," Papers 2406.07186, arXiv.org.
    6. Flynn, Joel P. & Sastry, Karthik A., 2023. "Strategic mistakes," Journal of Economic Theory, Elsevier, vol. 212(C).
    7. Andrew Caplin & Dániel CsabaQuantCo & John Leahy & Oded Nov, 2020. "Rational Inattention, Competitive Supply, and Psychometrics," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 135(3), pages 1681-1724.
    8. Cristina Gualdani & Shruti Sinha, 2023. "Identification in Discrete Choice Models with Imperfect Information," Working Papers 949, Queen Mary University of London, School of Economics and Finance.
    9. Eileen Tipoe & Abi Adams & Ian Crawford, 2022. "Revealed preference analysis and bounded rationality [Consume now or later? Time inconsistency, collective choice and revealed preference]," Oxford Economic Papers, Oxford University Press, vol. 74(2), pages 313-332.
    10. Kunal Pattanayak & Vikram Krishnamurthy, 2020. "Necessary and Sufficient Conditions for Inverse Reinforcement Learning of Bayesian Stopping Time Problems," Papers 2007.03481, arXiv.org, revised Mar 2023.
    11. Martin, Daniel & Muñoz-Rodriguez, Edwin, 2022. "Cognitive costs and misperceived incentives: Evidence from the BDM mechanism," European Economic Review, Elsevier, vol. 148(C).
    12. Persson, Petra, 2018. "Attention manipulation and information overload," Behavioural Public Policy, Cambridge University Press, vol. 2(1), pages 78-106, May.
    13. Weijie Zhong, 2018. "The Indirect Cost of Information," Papers 1809.00697, arXiv.org, revised Apr 2020.
    14. Pierre Fleckinger & Matthieu Glachant & Gabrielle Moineville, 2017. "Incentives for Quality in Friendly and Hostile Informational Environments," American Economic Journal: Microeconomics, American Economic Association, vol. 9(1), pages 242-274, February.
    15. Philippe Jehiel & Jakub Steiner, 2020. "Selective Sampling with Information-Storage Constraints [On interim rationality, belief formation and learning in decision problems with bounded memory]," The Economic Journal, Royal Economic Society, vol. 130(630), pages 1753-1781.
    16. Dirk Bergemann & Stephen Morris, 2019. "Information Design: A Unified Perspective," Journal of Economic Literature, American Economic Association, vol. 57(1), pages 44-95, March.
    17. Philippe Jehiel, 2022. "Analogy-Based Expectation Equilibrium and Related Concepts:Theory, Applications, and Beyond," Working Papers halshs-03735680, HAL.
    18. Larionov, Daniil & Pham, Hien & Yamashita, Takuro & Zhu, Shuguang, 2021. "First Best Implementation with Costly Information Acquisition," TSE Working Papers 21-1261, Toulouse School of Economics (TSE), revised Apr 2022.
    19. Jacob LaRiviere & Mikolaj Czajkowski & Nick Hanley & Katherine Simpson, 2016. "What is the Causal Impact of Knowledge on Preferences in Stated Preference Studies?," Working Papers 2016-12, Faculty of Economic Sciences, University of Warsaw.
    20. Bartosz Maćkowiak & Filip Matějka & Mirko Wiederholt, 2023. "Rational Inattention: A Review," Journal of Economic Literature, American Economic Association, vol. 61(1), pages 226-273, March.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2102.04594. See general information about how to correct material in RePEc.

    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 CitEc recognized a bibliographic reference but did not link an item in RePEc 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 RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.