IDEAS home Printed from https://ideas.repec.org/p/hal/wpaper/hal-00362643.html
   My bibliography  Save this paper

Online Multi-task Learning with Hard Constraints

Author

Listed:
  • Gabor Lugosi

    (ICREA - Institució Catalana de Recerca i Estudis Avançats = Catalan Institution for Research and Advanced Studies)

  • Omiros Papaspiliopoulos

    (ICREA - Institució Catalana de Recerca i Estudis Avançats = Catalan Institution for Research and Advanced Studies)

  • Gilles Stoltz

    (DMA - Département de Mathématiques et Applications - ENS-PSL (UMR8553) - ENS-PSL - École normale supérieure - Paris - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique, GREGH - Groupement de Recherche et d'Etudes en Gestion à HEC - HEC Paris - Ecole des Hautes Etudes Commerciales - CNRS - Centre National de la Recherche Scientifique)

Abstract

We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general class of tractable constraints, for which we introduce computationally efficient ways of selecting actions, essentially by reducing to an on-line shortest path problem. We briefly discuss ``tracking'' and ``bandit'' versions of the problem and extend the model in various ways, including non-additive global losses and uncountably infinite sets of tasks.

Suggested Citation

  • Gabor Lugosi & Omiros Papaspiliopoulos & Gilles Stoltz, 2009. "Online Multi-task Learning with Hard Constraints," Working Papers hal-00362643, HAL.
    • Handle: RePEc:hal:wpaper:hal-00362643
    Note: View the original document on HAL open archive server: https://hal.science/hal-00362643v2
    as

    Download full text from publisher

    File URL: https://hal.science/hal-00362643v2/document
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Mengel, Friederike, 2012. "Learning across games," Games and Economic Behavior, Elsevier, vol. 74(2), pages 601-619.
    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. Marco LiCalzi & Roland Mühlenbernd, 2022. "Feature-weighted categorized play across symmetric games," Experimental Economics, Springer;Economic Science Association, vol. 25(3), pages 1052-1078, June.
    2. Marchiori, Davide & Di Guida, Sibilla & Polonio, Luca, 2021. "Plasticity of strategic sophistication in interactive decision-making," Journal of Economic Theory, Elsevier, vol. 196(C).
    3. Florian Gauer & Christoph Kuzmics, 2020. "Cognitive Empathy In Conflict Situations," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 61(4), pages 1659-1678, November.
    4. Daniele Condorelli & Massimiliano Furlan, 2024. "Deep Learning to Play Games," Papers 2409.15197, arXiv.org.
    5. Philippe Jehiel, 2022. "Analogy-Based Expectation Equilibrium and Related Concepts:Theory, Applications, and Beyond," PSE Working Papers halshs-03735680, HAL.
    6. Wei James Chen & Joseph Tao-yi Wang, 2020. "A modified Monty Hall problem," Theory and Decision, Springer, vol. 89(2), pages 151-156, September.
    7. Lensberg, Terje & Schenk-Hoppé, Klaus Reiner, 2021. "Cold play: Learning across bimatrix games," Journal of Economic Behavior & Organization, Elsevier, vol. 185(C), pages 419-441.
    8. Jehiel, Philippe & Singh, Juni, 2021. "Multi-state choices with aggregate feedback on unfamiliar alternatives," Games and Economic Behavior, Elsevier, vol. 130(C), pages 1-24.
    9. Edward W. Piotrowski & Jan Sladkowski & Anna Szczypinska, "undated". "Reinforcement Learning in Market Games," Departmental Working Papers 30, University of Bialtystok, Department of Theoretical Physics.
    10. Daskalova, Vessela & Vriend, Nicolaas J., 2020. "Categorization and coordination," European Economic Review, Elsevier, vol. 129(C).
    11. Sawa, Ryoji & Zusai, Dai, 2019. "Evolutionary dynamics in multitasking environments," Journal of Economic Behavior & Organization, Elsevier, vol. 166(C), pages 288-308.
    12. Mohlin, Erik, 2014. "Optimal categorization," Journal of Economic Theory, Elsevier, vol. 152(C), pages 356-381.
    13. Mengel, Friederike & Sciubba, Emanuela, 2010. "Extrapolation in Games of Coordination and Dominance Solvable Games," Sustainable Development Papers 98475, Fondazione Eni Enrico Mattei (FEEM).
    14. Benndorf, Volker & Martínez-Martínez, Ismael & Normann, Hans-Theo, 2016. "Equilibrium selection with coupled populations in hawk–dove games: Theory and experiment in continuous time," Journal of Economic Theory, Elsevier, vol. 165(C), pages 472-486.
    15. Christoph March, 2011. "Adaptive social learning," PSE Working Papers halshs-00572528, HAL.
    16. Yuan Gu & Chao Hung Chan, 2024. "Complexity Aversion," Papers 2406.18463, arXiv.org.
    17. Philippe Jehiel & Giacomo Weber, 2023. "Calibrated Clustering and Analogy-Based Expectation Equilibrium," PSE Working Papers halshs-04154234, HAL.
    18. Mohlin, Erik, 2012. "Evolution of theories of mind," Games and Economic Behavior, Elsevier, vol. 75(1), pages 299-318.
    19. Valeria Maggian & Ludovica Spinola, 2024. "Spillover effects of cooperative behaviour when switching tasks: the role of gender," Working Papers 2024: 09, Department of Economics, University of Venice "Ca' Foscari".
    20. , & ,, 2008. "Contagion through learning," Theoretical Economics, Econometric Society, vol. 3(4), December.

    More about this item

    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:hal:wpaper:hal-00362643. 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: CCSD (email available below). General contact details of provider: https://hal.archives-ouvertes.fr/ .

    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.