skip to main content
10.1145/3055399.3084098acmconferencesArticle/Chapter ViewAbstractPublication PagesstocConference Proceedingsconference-collections
invited-talk

Fast convergence of learning in games (invited talk)

Published:19 June 2017Publication History

ABSTRACT

A plethora of recent work has analyzed properties of outcomes in games when each player employs a no-regret learning algorithm. Many algorithms achieve regret against the best fixed action in hindisght that decays at a rate of O(1/'T), when the game is played for T iterations. The latter rate is optimal in adversarial settings. However, in a game a player's opponents are minimizing their own regret, rather than maximizing the player's regret. (Daskalakis et al. 2014) and (Rakhlin and Sridharan 2013) showed that in two player zero-sum games O(1/T) rates are achievable. In (Syrgkanis et al. 2015), we show that O(1/T3/4) rates are achievable in general multi-player games and also analyze convergence of the dynamics to approximately optimal social welfare, where we show a convergence rate of O(1/T). The latter result was subsequently generalized to a broader class of learning algorithms by (Foster et al. 2016). This is based on joint work with Alekh Agarwal, Haipeng Luo and Robert E. Schapire.

Skip Supplemental Material Section

Supplemental Material

d1_sb_t3.mp4

References

  1. Avrim Blum, MohammadTaghi Hajiaghayi, Katrina Ligett, and Aaron Roth. 2008. Regret Minimization and the Price of Total Anarchy. In Proceedings of the Fortieth Annual ACM Symposium on Theory of Computing (STOC ’08). ACM, New York, NY, USA, 373–382. https:// Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. Nicolo Cesa-Bianchi and Gabor Lugosi. 2006. Prediction, Learning, and Games. Cambridge University Press, New York, NY, USA. Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. Constantinos Daskalakis, Alan Deckelbaum, and Anthony Kim. 2014. Nearoptimal no-regret algorithms for zero-sum games. Games and Economic Behavior 0 (2014), –. https://Google ScholarGoogle Scholar
  4. Dylan J Foster, Thodoris Lykouris, Karthik Sridharan, Eva Tardos, et al. 2016. Learning in games: Robustness of fast convergence. In Advances in Neural Information Processing Systems. 4727–4735.Google ScholarGoogle Scholar
  5. Yoav Freund and Robert E Schapire. 1997. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. J. Comput. System Sci. 55, 1 (1997), 119 – 139. Google ScholarGoogle ScholarDigital LibraryDigital Library
  6. Drew Fudenberg and David K. Levine. 1998. The Theory of Learning in Games. MIT Press, Cambridge, MA.Google ScholarGoogle Scholar
  7. Jyrki Kivinen and Manfred K. Warmuth. 1997. Exponentiated Gradient Versus Gradient Descent for Linear Predictors. Inf. Comput. 132, 1 (Jan. 1997), 1–63. https:// Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. Nick Littlestone and Manfred K Warmuth. 1994. The weighted majority algorithm. Information and computation 108, 2 (1994), 212–261. Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. Alexander Rakhlin and Karthik Sridharan. 2013. Online Learning with Predictable Sequences. In COLT 2013. 993–1019.Google ScholarGoogle Scholar
  10. Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, and Robert E Schapire. 2015. Fast convergence of regularized learning in games. In Advances in Neural Information Processing Systems. 2989–2997. Google ScholarGoogle ScholarDigital LibraryDigital Library
  11. Abstract 1 Introduction ReferencesGoogle ScholarGoogle Scholar

Index Terms

  1. Fast convergence of learning in games (invited talk)

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in
    • Published in

      cover image ACM Conferences
      STOC 2017: Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing
      June 2017
      1268 pages
      ISBN:9781450345286
      DOI:10.1145/3055399

      Copyright © 2017 Owner/Author

      Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 19 June 2017

      Check for updates

      Qualifiers

      • invited-talk

      Acceptance Rates

      Overall Acceptance Rate1,469of4,586submissions,32%

      Upcoming Conference

      STOC '24
      56th Annual ACM Symposium on Theory of Computing (STOC 2024)
      June 24 - 28, 2024
      Vancouver , BC , Canada
    • Article Metrics

      • Downloads (Last 12 months)1
      • Downloads (Last 6 weeks)0

      Other Metrics

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader