Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

First-order (coarse) correlated equilibria in non-concave games (2403.18174v3)

Published 27 Mar 2024 in cs.GT

Abstract: We investigate first-order notions of correlated equilibria; distributions of actions for smooth, potentially non-concave games such that players do not incur any regret against small modifications to their strategies along a set of continuous vector fields. We define two such notions, based on local deviations and on stationarity of the distribution, and identify the notion of coarseness as the setting where the associated vector fields are in fact gradient fields. For coarse equilibria, we prove that online (projected) gradient decent has a universal approximation property for both variants of equilibrium. In the non-coarse setting, we instead reduce the problem of finding an equilibrium to fixed-point computation via the usual framework of $\Phi$-regret minimisation, and identify tractable instances. Finally, we study the primal-dual framework to our notion of first-order equilibria. For coarse equilibria defined by a family of functions, we find that a dual bound on the worst-case expectation of a performance metric takes the form of a generalised Lyapunov function for the dynamics of the game. Specifically, usual primal-dual price of anarchy analysis for coarse correlated equilibria as well as the smoothness framework of Roughgarden are both equivalent to a problem of general Lyapunov function estimation. For non-coarse equilibria, we instead observe a vector field fit problem for the gradient dynamics of the game. These follow from containment results in normal form games; the usual notion of a (coarse) correlated equilibria is equivalent to our first-order local notions of (coarse) correlated equilibria with respect to an appropriately chosen set of vector fields.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (75)
  1. On the uniqueness of Bayesian coarse correlated equilibria in standard first-price and all-pay auctions, 2024.
  2. Near-optimal no-regret learning for correlated equilibria in multi-player general-sum games. In Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing, pages 736–749, 2022.
  3. Linear Programming in Infinite-dimensional Spaces: Theory and Applications. A Wiley-Interscience publication. Wiley, 1987.
  4. Learning in matrix games can be arbitrarily complex. In Mikhail Belkin and Samory Kpotufe, editors, Proceedings of Thirty Fourth Conference on Learning Theory, volume 134 of Proceedings of Machine Learning Research, pages 159–185. PMLR, 15-19 Aug 2021.
  5. No-regret learning in games is turing complete. arXiv preprint arXiv:2202.11871, 2022.
  6. The price of stability for network design with fair cost allocation. SIAM Journal on Computing, 38(4):1602–1623, 2008.
  7. Multiplicative weights update in zero-sum games. In Proceedings of the 2018 ACM Conference on Economics and Computation, pages 321–338. ACM, 2018.
  8. Perturbations of set-valued dynamical systems, with applications to game theory. Dynamic Games and Applications, 2:195–205, 2012.
  9. First-price auctions with general information structures: Implications for bidding and revenue. Econometrica, 85(1):107–143, 2017.
  10. Ulrich Berger. Fictitious play in 2 ×\times× n games. Journal of Economic Theory, 120(2):139–154, 2005.
  11. Learning equilibria in symmetric auction games using artificial neural networks. Nature Machine Intelligence, 3:687–695, 2021.
  12. Computing Bayes-Nash equilibrium in auction games via gradient dynamics. Operations Research, to appear, 2023.
  13. Vittorio Bilò. A unifying tool for bounding the quality of non-cooperative solutions in weighted congestion games. Theory of Computing Systems, 62:1288–1317, 2018.
  14. Selling to a no-regret buyer. In Proceedings of the 2018 ACM Conference on Economics and Computation, pages 523–538, 2018.
  15. George W Brown. Iterative solution of games by fictitious play. Activity analysis of production and allocation, 13(1):374–376, 1951.
  16. On local equilibrium in non-concave games, 2024.
  17. Simultaneous Bayesian auctions and computational complexity. In Proceedings of the Fifteenth ACM Conference on Economics and Computation, EC ’14, page 895–910, New York, NY, USA, 2014. Association for Computing Machinery.
  18. Prediction, learning, and games. Cambridge university press, 2006.
  19. Xi Chen and Xiaotie Deng. Settling the complexity of two-player Nash equilibrium. In Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science, FOCS ’06, page 261–272, USA, 2006. IEEE Computer Society.
  20. Xi Chen and Binghui Peng. Hedging in games: Faster convergence of external and swap regrets. Advances in Neural Information Processing Systems, 33:18990–18999, 2020.
  21. Xi Chen and Binghui Peng. Complexity of equilibria in first-price auctions under general tie-breaking rules. arXiv preprint arXiv:2303.16388, 2023.
  22. Vortices instead of equilibria in minmax optimization: Chaos and butterfly effects of online learning in zero-sum games. In Proceedings of Thirty Second Conference on Learning Theory, volume 99 of Proceedings of Machine Learning Research, pages 807–834. PMLR, 2021.
  23. Bayesian combinatorial auctions. Journal of the ACM (JACM), 63(2):1–19, 2016.
  24. Tight bounds for the price of anarchy of simultaneous first-price auctions. ACM Transactions on Economics and Computation (TEAC), 4(2):1–33, 2016.
  25. Existence of solutions to projected differential equations in hilbert spaces. Proceedings of the American Mathematical Society, 132(1):183–193, 2004.
  26. New complexity results about Nash equilibria. Games and Economic Behavior, 63(2):621–641, 2008. Second World Congress of the Game Theory Society.
  27. Constantinos Daskalakis. On the complexity of approximating a Nash equilibrium. ACM Transactions on Algorithms (TALG), 9(3):1–35, 2013.
  28. Constantinos Daskalakis. Non-concave games: A challenge for game theory’s next 100 years. In Cowles Preprints, 2022.
  29. The complexity of computing a Nash equilibrium. SIAM Journal on Computing, 39(1):195–259, 2009.
  30. The complexity of constrained min-max optimization. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, pages 1466–1478, 2021.
  31. Nash convergence of mean-based learning algorithms in first price auctions. In Proceedings of the ACM Web Conference 2022, pages 141–150, 2022.
  32. Dynamical systems and variational inequalities. Annals of Operations Research, 44:7–42, 1993.
  33. Correlated and coarse equilibria of single-item auctions. In Yang Cai and Adrian Vetta, editors, Web and Internet Economics, pages 131–144, Berlin, Heidelberg, 2016. Springer Berlin Heidelberg.
  34. Convergence analysis of no-regret bidding algorithms in repeated auctions. volume 35, pages 5399–5406, 2021.
  35. On matrices with non-positive off-diagonal elements and positive principal minors. Czechoslovak Mathematical Journal, 12(3):382–400, 1962.
  36. On the complexity of equilibrium computation in first-price auctions. In Proceedings of the 22nd ACM Conference on Economics and Computation, pages 454–476, 2021.
  37. Bounding stationary expectations of markov processes. In Markov processes and related topics: a Festschrift for Thomas G. Kurtz, volume 4, pages 195–215. Institute of Mathematical Statistics, 2008.
  38. Geoffrey J Gordon. No-regret algorithms for structured prediction problems. Carnegie Mellon University. Center for Automated Learning and Discovery, 2005.
  39. No-regret learning in convex games. In Proceedings of the 25th International Conference on Machine Learning, pages 360–367, 2008.
  40. Bounds for regret-matching algorithms. In AI&M, 2006.
  41. Regret minimization in stochastic non-convex learning via a proximal-gradient approach. In International Conference on Machine Learning, pages 4008–4017. PMLR, 2021.
  42. John C. Harsanyi and Reinhard Selten, editors. A general theory of equilibrium selection in games. MIT Press, 1st edition, 1988.
  43. Computational equivalence of fixed points and no regret algorithms, and convergence to equilibria. Advances in Neural Information Processing Systems, 20, 2007.
  44. Efficient regret minimization in non-convex games. In International Conference on Machine Learning, pages 1433–1441. PMLR, 2017.
  45. On the diffusion approximation of nonconvex stochastic gradient descent. Annals of Mathematical Sciences and Applications, 4(1), 2019.
  46. Settling the efficiency of the first-price auction. SIGecom Exch, 20:69–74, 2022.
  47. Worst-case equilibria. Computer science review, 3(2):65–69, 2009.
  48. Sequential auctions and externalities. In Proceedings of the twenty-third annual ACM-SIAM symposium on Discrete Algorithms, pages 869–886. SIAM, 2012.
  49. On the convergence of stochastic gradient descent with adaptive stepsizes. In The 22nd international conference on artificial intelligence and statistics, pages 983–992. PMLR, 2019.
  50. Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks. arXiv preprint arXiv:2211.15936, 2022.
  51. Learning in games with continuous action sets and unknown payoff functions. Math. Program., 173(1–2):465–507, jan 2019.
  52. Nash, Conley, and computation: Impossibility and incompleteness in game dynamics, 2022.
  53. Potential games. Games and economic behavior, 14(1):124–143, 1996.
  54. Walking in the shadow: A new perspective on descent directions for constrained minimization. Advances in neural information processing systems, 33:12873–12883, 2020.
  55. The limits of smoothness: A primal-dual framework for price of anarchy bounds. In International Workshop on Internet and Network Economics, pages 319–326. Springer, 2010.
  56. Projected dynamical systems and variational inequalities with applications, volume 2. Springer Science & Business Media, 2012.
  57. John F. Nash. Equilibrium points in n𝑛nitalic_n-person games. Proceedings of the National Academy of Sciences, 36(1):48–49, 1950.
  58. Kim Thang Nguyen. Primal-Dual Approaches in Online Algorithms, Algorithmic Game Theory and Online Learning. Habilitation à diriger des recherches, Université Paris Sorbonne, June 2019.
  59. Multiplicative weights update with constant step-size in congestion games: Convergence, limit cycles and chaos. Advances in Neural Information Processing Systems, 30, 2017.
  60. Average case performance of replicator dynamics in potential games via computing regions of attraction. In Proceedings of the 2016 ACM Conference on Economics and Computation, pages 703–720, 2016.
  61. Game dynamics as the meaning of a game. SIGecom Exch., 16(2):53–63, May 2019.
  62. Julia Robinson. An iterative method of solving a game. Annals of mathematics, pages 296–301, 1951.
  63. J. Ben Rosen. Existence and uniqueness of equilibrium points for concave n𝑛nitalic_n-person games. Econometrica: Journal of the Econometric Society, pages 520–534, 1965.
  64. Tim Roughgarden. Selfish routing and the price of anarchy. MIT press, 2005.
  65. Tim Roughgarden. Intrinsic robustness of the price of anarchy. Journal of the ACM (JACM), 62(5):1–42, 2015.
  66. Beating price of anarchy and gradient descent without regret in potential games. In The Twelfth International Conference on Learning Representations, 2024.
  67. William H Sandholm. Evolutionary game theory. Complex Social and Behavioral Systems: Game Theory and Agent-Based Models, pages 573–608, 2020.
  68. Andreas S. Schulz and Nicolás E. Stier Moses. On the performance of user equilibria in traffic networks. In SODA, volume 3, pages 86–87, 2003.
  69. Alexander Shapiro. On duality theory of conic linear problems. Nonconvex Optimization and its Applications, 57:135–155, 2001.
  70. Lloyd Shapley. Some topics in two-person games. Advances in game theory, 52:1–29, 1964.
  71. Learning correlated equilibria in games with compact sets of strategies. Games and Economic Behavior, 59(1):187–208, 2007.
  72. On the convergence of distributed projected gradient play with heterogeneous learning rates in monotone games. Systems & Control Letters, 182:105654, 2023.
  73. Adrian Vetta. Nash equilibria in competitive societies, with applications to facility location, traffic routing and auctions. In The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings., pages 416–425. IEEE, 2002.
  74. H. Peyton Young. Strategic learning and its limits. Oxford University Press, 2004.
  75. Learning in games with lossy feedback. Advances in Neural Information Processing Systems, 31, 2018.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets