Playing Anonymous Games using Simple Strategies

We investigate the complexity of computing approximate Nash equilibria in anonymous games. Our main algorithmic result is the following: For any $n$-player anonymous game with a bounded number of strategies and any constant $\delta>0$, an $O(1/n^{1-\delta})$-approximate Nash equilibrium can be computed in polynomial time. Complementing this positive result, we show that if there exists any constant $\delta>0$ such that an $O(1/n^{1+\delta})$-approximate equilibrium can be computed in polynomial time, then there is a fully polynomial-time approximation scheme for this problem. We also present a faster algorithm that, for any $n$-player $k$-strategy anonymous game, runs in time $\tilde O((n+k) k n^k)$ and computes an $\tilde O(n^{-1/3} k^{11/3})$-approximate equilibrium. This algorithm follows from the existence of simple approximate equilibria of anonymous games, where each player plays one strategy with probability $1-\delta$, for some small $\delta$, and plays uniformly at random with probability $\delta$. Our approach exploits the connection between Nash equilibria in anonymous games and Poisson multinomial distributions (PMDs). Specifically, we prove a new probabilistic lemma establishing the following: Two PMDs, with large variance in each direction, whose first few moments are approximately matching are close in total variation distance. Our structural result strengthens previous work by providing a smooth tradeoff between the variance bound and the number of matching moments.

[1]  Daniel M. Kane,et al.  Properly Learning Poisson Binomial Distributions in Almost Polynomial Time , 2015, COLT.

[2]  M. Blonski Anonymous Games with Binary Actions , 1999 .

[3]  I. Milchtaich,et al.  Congestion Games with Player-Specific Payoff Functions , 1996 .

[4]  Christos H. Papadimitriou,et al.  Discretized Multinomial Distributions and Nash Equilibria in Anonymous Games , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[5]  Aranyak Mehta,et al.  Playing large games using simple strategies , 2003, EC '03.

[6]  M. Blonski The women of Cairo Equilibria in large anonymous games , 2005 .

[7]  Christos H. Papadimitriou,et al.  On oblivious PTAS's for nash equilibrium , 2009, STOC '09.

[8]  Anindya De,et al.  A size-free CLT for poisson multinomials and its applications , 2015, STOC.

[9]  Daniel M. Kane,et al.  The fourier transform of poisson multinomial distributions and its algorithmic applications , 2015, STOC.

[10]  Paul W. Goldberg,et al.  Query Complexity of Approximate Equilibria in Anonymous Games , 2015, WINE.

[11]  Paul W. Goldberg,et al.  The Complexity of Computing a Nash Equilibrium , 2009, SIAM J. Comput..

[12]  H. Simon,et al.  Models of Bounded Rationality: Empirically Grounded Economic Reason , 1997 .

[13]  C. Papadimitriou,et al.  Computing Equilibria in Anonymous Games , 2007, FOCS 2007.

[14]  Christos H. Papadimitriou,et al.  Approximate Nash equilibria in anonymous games , 2015, J. Econ. Theory.

[15]  Daniel M. Kane,et al.  Optimal Learning via the Fourier Transform for Sums of Independent Integer Random Variables , 2015, COLT.

[16]  Aviad Rubinstein Settling the Complexity of Computing Approximate Two-Player Nash Equilibria , 2016, FOCS.

[17]  H. Simon Models of Bounded Rationality: Empirically Grounded Economic Reason , 1997 .

[18]  Xi Chen,et al.  On the Complexity of Nash Equilibria in Anonymous Games , 2014, STOC.

[19]  Eran Shmaya,et al.  Lipschitz Games , 2013, Math. Oper. Res..