The Lipschitz Constant of Perturbed Anonymous Games

04/30/2020
by   Ron Peretz, et al.
0

The worst-case Lipschitz constant of an n-player k-action δ-perturbed game, λ(n,k,δ), is given an explicit probabilistic description. In the case of k≥ 3, λ(n,k,δ) is identified with the passage probability of a certain symmetric random walk on ℤ. In the case of k=2 and n even, λ(n,2,δ) is identified with the probability that two two i.i.d. Binomial random variables are equal. The remaining case, k=2 and n odd, is bounded through the adjacent (even) values of n. Our characterisation implies a sharp closed form asymptotic estimate of λ(n,k,δ) as δ n /k→∞.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/20/2022

PPAD-Complete Pure Approximate Nash Equilibria in Lipschitz Games

Lipschitz games, in which there is a limit λ (the Lipschitz value of the...
research
09/10/2019

Golden games

We consider extensive form win-lose games over a complete binary-tree of...
research
10/10/2018

Combining Bayesian Optimization and Lipschitz Optimization

Bayesian optimization and Lipschitz optimization have developed alternat...
research
07/08/2021

Lower Bounds for the Query Complexity of Equilibria in Lipschitz Games

Nearly a decade ago, Azrieli and Shmaya introduced the class of λ-Lipsch...
research
03/15/2021

Distribution Privacy Under Function Recoverability

A user generates n independent and identically distributed data random v...
research
06/14/2022

A Stochastic Proximal Method for Nonsmooth Regularized Finite Sum Optimization

We consider the problem of training a deep neural network with nonsmooth...

Please sign up or login with your details

Forgot password? Click here to reset