Abstract

Given two bounded convex sets $$X\subseteq \mathbb R^m$$ and $$Y\subseteq \mathbb R^n,$$ specified by membership oracles, and a continuous convex–concave function $$F:X\times Y\rightarrow \mathbb R$$ , we consider the problem of computing an $$\varepsilon $$ -approximate saddle point, that is, a pair $$(x^*,y^*)\in X\times Y$$ such that $$\sup _{y\in Y} F(x^*,y)\le \inf _{x\in X}F(x,y^*)+\varepsilon .$$ Grigoriadis and Khachiyan (Oper Res Lett 18(2):53–58, 1995) gave a simple randomized variant of fictitious play for computing an $$\varepsilon $$ -approximate saddle point for matrix games, that is, when $$F$$ is bilinear and the sets $$X$$ and $$Y$$ are simplices. In this paper, we extend their method to the general case. In particular, we show that, for functions of constant “width”, an $$\varepsilon $$ -approximate saddle point can be computed using $$O^* \big (\frac{(n+m)}{\varepsilon ^2}\ln R \big )$$ random samples from log-concave distributions over the convex sets $$X$$ and $$Y$$ . It is assumed that $$X$$ and $$Y$$ have inscribed balls of radius $$1/R$$ and circumscribing balls of radius $$R$$ . As a consequence, we obtain a simple randomized polynomial-time algorithm that computes such an approximation faster than known methods for problems with bounded width and when $$\varepsilon \in (0,1)$$ is a fixed, but arbitrarily small constant. Our main tool for achieving this result is the combination of the randomized fictitious play with the recently developed results on sampling from convex sets.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call