A size-free CLT for poisson multinomials and its applications

Constantinos Daskalakis, Anindya De, Gautam Kamath, Christos Tzamos
2016 Proceedings of the 48th Annual ACM SIGACT Symposium on Theory of Computing - STOC 2016  
An (n,k)-Poisson Multinomial Distribution (PMD) is the distribution of the sum of n independent random vectors supported on the set B_k={e_1,...,e_k} of standard basis vectors in R^k. We show that any (n,k)-PMD is poly(kσ)-close in total variation distance to the (appropriately discretized) multi-dimensional Gaussian with the same first two moments, removing the dependence on n from the Central Limit Theorem of Valiant and Valiant. Interestingly, our CLT is obtained by bootstrapping the
more » ... Valiant CLT itself through the structural characterization of PMDs shown in recent work by Daskalakis, Kamath, and Tzamos. In turn, our stronger CLT can be leveraged to obtain an efficient PTAS for approximate Nash equilibria in anonymous games, significantly improving the state of the art, and matching qualitatively the running time dependence on n and 1/ε of the best known algorithm for two-strategy anonymous games. Our new CLT also enables the construction of covers for the set of (n,k)-PMDs, which are proper and whose size is shown to be essentially optimal. Our cover construction combines our CLT with the Shapley-Folkman theorem and recent sparsification results for Laplacian matrices by Batson, Spielman, and Srivastava. Our cover size lower bound is based on an algebraic geometric construction. Finally, leveraging the structural properties of the Fourier spectrum of PMDs we show that these distributions can be learned from O_k(1/ε^2) samples in poly_k(1/ε)-time, removing the quasi-polynomial dependence of the running time on 1/ε from the algorithm of Daskalakis, Kamath, and Tzamos.
doi:10.1145/2897518.2897519 dblp:conf/stoc/DaskalakisDKT16 fatcat:ymocsnx5evgwnhgdc3ysltpzm4