IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2502.19525.html
   My bibliography  Save this paper

Differentially Private Sequential Learning

Author

Listed:
  • Yuxin Liu
  • M. Amin Rahimian

Abstract

In a differentially private sequential learning setting, agents introduce endogenous noise into their actions to maintain privacy. Applying this to a standard sequential learning model leads to different outcomes for continuous vs. binary signals. For continuous signals with a nonzero privacy budget, we introduce a novel smoothed randomized response mechanism that adapts noise based on distance to a threshold, unlike traditional randomized response, which applies uniform noise. This enables agents' actions to better reflect both private signals and observed history, accelerating asymptotic learning speed to $\Theta_{\epsilon}(\log(n))$, compared to $\Theta(\sqrt{\log(n)})$ in the non-private regime where privacy budget is infinite. Moreover, in the non-private setting, the expected stopping time for the first correct decision and the number of incorrect actions diverge, meaning early agents may make mistakes for an unreasonably long period. In contrast, under a finite privacy budget $\epsilon \in (0,1)$, both remain finite, highlighting a stark contrast between private and non-private learning. Learning with continuous signals in the private regime is more efficient, as smooth randomized response enhances the log-likelihood ratio over time, improving information aggregation. Conversely, for binary signals, differential privacy noise hinders learning, as agents tend to use a constant randomized response strategy before an information cascade forms, reducing action informativeness and hampering the overall process.

Suggested Citation

  • Yuxin Liu & M. Amin Rahimian, 2025. "Differentially Private Sequential Learning," Papers 2502.19525, arXiv.org, revised Apr 2025.
  • Handle: RePEc:arx:papers:2502.19525
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2502.19525
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Lones Smith & Peter Sorensen, 2000. "Pathological Outcomes of Observational Learning," Econometrica, Econometric Society, vol. 68(2), pages 371-398, March.
    2. Yanzhe (Murray) Lei & Sentao Miao & Ruslan Momot, 2024. "Privacy-Preserving Personalized Revenue Management," Management Science, INFORMS, vol. 70(7), pages 4875-4892, July.
    3. Xi Chen & David Simchi-Levi & Yining Wang, 2022. "Privacy-Preserving Dynamic Personalized Pricing with Demand Learning," Management Science, INFORMS, vol. 68(7), pages 4878-4898, July.
    4. Dinah Rosenberg & Nicolas Vieille, 2019. "On the Efficiency of Social Learning," Econometrica, Econometric Society, vol. 87(6), pages 2141-2168, November.
    5. Hann-Caruthers, Wade & Martynov, Vadim V. & Tamuz, Omer, 2018. "The speed of sequential asymptotic learning," Journal of Economic Theory, Elsevier, vol. 173(C), pages 383-409.
    6. Bohren, J. Aislinn, 2016. "Informational herding with model misspecification," Journal of Economic Theory, Elsevier, vol. 163(C), pages 222-247.
    7. Ali, S. Nageeb, 2018. "Herding with costly information," Journal of Economic Theory, Elsevier, vol. 175(C), pages 713-729.
    8. Bikhchandani, Sushil & Hirshleifer, David & Welch, Ivo, 1992. "A Theory of Fads, Fashion, Custom, and Cultural Change in Informational Cascades," Journal of Political Economy, University of Chicago Press, vol. 100(5), pages 992-1026, October.
    9. Abhijit V. Banerjee, 1992. "A Simple Model of Herd Behavior," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 107(3), pages 797-817.
    Full references (including those not matched with items on IDEAS)

    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. Sushil Bikhchandani & David Hirshleifer & Omer Tamuz & Ivo Welch, 2024. "Information Cascades and Social Learning," Journal of Economic Literature, American Economic Association, vol. 62(3), pages 1040-1093, September.
    2. Mira Frick & Ryota Iijima & Yuhta Ishii, 2020. "Belief Convergence under Misspecified Learning: A Martingale Approach," Cowles Foundation Discussion Papers 2235R, Cowles Foundation for Research in Economics, Yale University, revised Mar 2021.
    3. Mira Frick & Ryota Iijima & Yuhta Ishii, 2020. "Misinterpreting Others and the Fragility of Social Learning," Econometrica, Econometric Society, vol. 88(6), pages 2281-2328, November.
    4. Mira Frick & Ryota Iijima & Yuhta Ishii, 2020. "Belief Convergence under Misspecified Learning: A Martingale Approach," Cowles Foundation Discussion Papers 2235R3, Cowles Foundation for Research in Economics, Yale University, revised Apr 2022.
    5. Xuanye Wang, 2021. "Fragility of Confounded Learning," Papers 2106.07712, arXiv.org.
    6. Philippe Jehiel, 2022. "Analogy-Based Expectation Equilibrium and Related Concepts:Theory, Applications, and Beyond," Working Papers halshs-03735680, HAL.
    7. Bohren, Aislinn & Hauser, Daniel, 2017. "Learning with Heterogeneous Misspecified Models: Characterization and Robustness," CEPR Discussion Papers 12036, C.E.P.R. Discussion Papers.
    8. Stephanie De Mel & Kaivan Munshi & Soenje Reiche & Hamid Sabourian, 2021. "Herding with Heterogeneous Ability: An Application to Organ Transplantation," Cowles Foundation Discussion Papers 2308, Cowles Foundation for Research in Economics, Yale University.
    9. Fernández-Duque, Mauricio, 2022. "The probability of pluralistic ignorance," Journal of Economic Theory, Elsevier, vol. 202(C).
    10. Bobkova, Nina & Mass, Helene, 2022. "Two-dimensional information acquisition in social learning," Journal of Economic Theory, Elsevier, vol. 202(C).
    11. Penczynski, Stefan P., 2017. "The nature of social learning: Experimental evidence," European Economic Review, Elsevier, vol. 94(C), pages 148-165.
    12. Dasaratha, Krishna & He, Kevin, 2020. "Network structure and naive sequential learning," Theoretical Economics, Econometric Society, vol. 15(2), May.
    13. Florian Brandl, 2025. "The Social Learning Barrier," Papers 2504.12136, arXiv.org.
    14. Daron Acemoglu & Ali Makhdoumi & Azarakhsh Malekian & Asuman Ozdaglar, 2017. "Fast and Slow Learning From Reviews," NBER Working Papers 24046, National Bureau of Economic Research, Inc.
    15. Ilai Bistritz & Nasimeh Heydaribeni & Achilleas Anastasopoulos, 2019. "Do Informational Cascades Happen with Non-myopic Agents?," Papers 1905.01327, arXiv.org, revised Jul 2022.
    16. Christoph March & Anthony Ziegelmeyer, 2018. "Excessive Herding in the Laboratory: The Role of Intuitive Judgments," CESifo Working Paper Series 6855, CESifo.
    17. Bogaçhan Çelen & Sen Geng & Huihui Li, 2018. "Belief Error and Non-Bayesian Social Learning: An Experimental Evidence," GRU Working Paper Series GRU_2018_022, City University of Hong Kong, Department of Economics and Finance, Global Research Unit.
    18. Cunha, Douglas & Monte, Daniel, 2023. "Diversity Fosters Learning in Environments with Experimentation and Social Learning," MPRA Paper 117095, University Library of Munich, Germany.
    19. Mira Frick & Ryota Iijima & Yuhta Ishii, 2020. "Stability and Robustness in Misspecified Learning Models," Cowles Foundation Discussion Papers 2235, Cowles Foundation for Research in Economics, Yale University.
    20. Zhang, Min, 2021. "Non-monotone social learning," Journal of Economic Behavior & Organization, Elsevier, vol. 185(C), pages 565-579.

    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:2502.19525. 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.