Skip to main content
SpringerLink
Log in
Book cover

International Conference on Web and Internet Economics

WINE 2018: Web and Internet Economics pp 168–187Cite as

Learning Convex Partitions and Computing Game-Theoretic Equilibria from Best Response Queries

  • Conference paper
  • First Online:

  • 960 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 11316))

Abstract

Suppose that an m-simplex is partitioned into n convex regions having disjoint interiors and distinct labels, and we may learn the label of any point by querying it. The learning objective is to know, for any point in the simplex, a label that occurs within some distance \(\varepsilon \) from that point. We present two algorithms for this task: Constant-Dimension Generalised Binary Search (CD-GBS), which for constant m uses \(poly(n, \log \left( \frac{1}{\varepsilon } \right) )\) queries, and Constant-Region Generalised Binary Search (CR-GBS), which uses CD-GBS as a subroutine and for constant n uses \(poly(m, \log \left( \frac{1}{\varepsilon } \right) )\) queries. We show via Kakutani’s fixed-point theorem that these algorithms provide bounds on the best-response query complexity of computing approximate well-supported equilibria of bimatrix games in which one of the players has a constant number of pure strategies.

Full Online Version of Paper: https://arxiv.org/abs/1807.06170.

F. J. Marmolejo Cossío—Supported by the Mexican National Council of Science and Technology (CONACyT).

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    CD-GBS runs in polynomial time for constant m. The time-intensive operation consists of identifying uncovered intervals, but since the dimension of the ambient simplex is constant, each empirical polytope \({\widehat{P}}_i\) has at most a constant number of bounding hyperplanes. These hyperplanes can each be extruded by \(\varepsilon \), and checking whether there exists a point outside all these extrusions can be done in time polynomial in n via brute force. In fact, all other algorithms in this paper have efficient runtimes (in their relevant parameters) due to similar reasoning.

References

  1. Babichenko, Y.: Query complexity of approximate Nash equilibria. J. ACM 63(4), 36:1–36:24 (2016)

    Article  MathSciNet  Google Scholar 

  2. Babichenko, Y., Rubinstein, A.: Communication complexity of approximate Nash equilibria. In: Proceedings of the 49th STOC, pp. 878–889. ACM (2017)

    Google Scholar 

  3. Babichenko, Y., Barman, S., Peretz, R.: Empirical distribution of equilibrium play and its testing application. Math. Oper. Res. 42(1), 15–29 (2017)

    Article  MathSciNet  Google Scholar 

  4. Baldwin, E., Klemperer, P.: Understanding preferences: “demand types”, and the existence of equilibrium with indivisibilities. Technical report, LSE, October 2016

    Google Scholar 

  5. Brown, G.W.: Some notes on computation of game solutions. RAND corporation report, p. 78, April 1949

    Google Scholar 

  6. Bshouty, N.H., Goldberg, P.W., Goldman, S.A., Mathias, H.D.: Exact learning of discretized geometric concepts. SIAM J. Comput. 28(2), 674–699 (1998)

    Article  MathSciNet  Google Scholar 

  7. Chen, X., Deng, X., Teng, S.-H.: Settling the complexity of computing two-player Nash equilibria. J. ACM 56(3), 14:1–14:57 (2009)

    Article  MathSciNet  Google Scholar 

  8. Daskalakis, C., Pan, Q.: A counter-example to Karlin’s strong conjecture for fictitious play. In: Proceedings of 55th FOCS, pp. 11–20 (2014)

    Google Scholar 

  9. Daskalakis, C., Goldberg, P.W., Papadimitriou, C.H.: The complexity of computing a Nash equilibrium. SIAM J. Comput. 39(1), 195–259 (2009)

    Article  MathSciNet  Google Scholar 

  10. Fearnley, J., Gairing, M., Goldberg, P.W., Savani, R.: Learning equilibria of games via payoff queries. J. Mach. Learn. Res. 16, 1305–1344 (2015)

    MathSciNet  MATH  Google Scholar 

  11. Fudenberg, D., Levine, D.K.: The Theory of Learning in Games. MIT Press, Cambridge (1998)

    MATH  Google Scholar 

  12. Goldberg, P.W., Kwek, S.: The precision of query points as a resource for learning convex polytopes with membership queries. In: Proceedings of the 13th COLT, pp. 225–235 (2000)

    Google Scholar 

  13. Goldberg, P.W., Roth, A.: Bounds for the query complexity of approximate equilibria. ACM Trans. Econ. Comput. 4(4), 24:1–24:25 (2016)

    Article  MathSciNet  Google Scholar 

  14. Goldberg, P.W., Savani, R., Sørensen, T.B., Ventre, C.: On the approximation performance of fictitious play in finite games. Int. J. Game Theory 42(4), 1059–1083 (2013)

    Article  MathSciNet  Google Scholar 

  15. Goldberg, P.W., Turchetta, S.: Query complexity of approximate equilibria in anonymous games. J. Comput. Syst. Sci. 90, 80–98 (2017)

    Article  MathSciNet  Google Scholar 

  16. Hart, S., Mansour, Y.: How long to equilibrium? The communication complexity of uncoupled equilibrium procedures. Games Econ. Behav. 69(1), 107–126 (2010)

    Article  MathSciNet  Google Scholar 

  17. Hart, S., Nisan, N.: The query complexity of correlated equilibria. Games and Economic Behavior (2016). ISSN 0899–8256

    Google Scholar 

  18. Kakutani, S.: A generalization of Brouwer’s fixed point theorem. Duke Math. J. 8(3), 457–459 (1941)

    Article  MathSciNet  Google Scholar 

  19. Klemperer, P.: The product-mix auction: a new auction design for differentiated goods. J. Eur. Econ. Assoc. 8(2/3), 526–536 (2010)

    Article  Google Scholar 

  20. Lipton, R.J., Markakis, E., Mehta, A.: Playing large games using simple strategies. In: Proceedings of the 4th ACM-EC, EC 2003, pp. 36–41. ACM, New York (2003)

    Google Scholar 

  21. Nash, J.: Non-cooperative games. Ann. Math. 54(2), 286–295 (1951)

    Article  MathSciNet  Google Scholar 

  22. Robinson, J.: An iterative method of solving a game. Ann. Math. 54(2), 296–301 (1951)

    Article  MathSciNet  Google Scholar 

  23. Von Stengel, B.: Leadership with commitment to mixed strategies. CDAM Research report (2004)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Oxford, Oxford, UK

    Paul W. Goldberg & Francisco J. Marmolejo-Cossío

Authors
  1. Paul W. Goldberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Francisco J. Marmolejo-Cossío
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Paul W. Goldberg .

Editor information

Editors and Affiliations

  1. University of Liverpool, Liverpool, UK

    George Christodoulou

  2. Universität Augsburg, Augsburg, Germany

    Tobias Harks

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Goldberg, P.W., Marmolejo-Cossío, F.J. (2018). Learning Convex Partitions and Computing Game-Theoretic Equilibria from Best Response Queries. In: Christodoulou, G., Harks, T. (eds) Web and Internet Economics. WINE 2018. Lecture Notes in Computer Science(), vol 11316. Springer, Cham. https://doi.org/10.1007/978-3-030-04612-5_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-04612-5_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-04611-8

  • Online ISBN: 978-3-030-04612-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation