We develop new parameter-free and scale-free algorithms for solving convex-concave saddle-point problems. Our results are based on a new simple regret minimizer, the Conic Blackwell Algorithm$^+$ (CBA$^+$), which attains $O(1/\sqrt{T})$ average regret. Intuitively, our approach generalizes to other decision sets of interest ideas from the Counterfactual Regret minimization (CFR$^+$) algorithm, which has very strong practical performance for solving sequential games on simplexes. We show how to implement CBA$^+$ for the simplex, $\ell_{p}$ norm balls, and ellipsoidal confidence regions in the simplex, and we present numerical experiments for solving matrix games and distributionally robust optimization problems. Our empirical results show that CBA$^+$ is a simple algorithm that outperforms state-of-the-art methods on synthetic data and real data instances, without the need for any choice of step sizes or other algorithmic parameters.
翻译:我们开发了无参数和无比例的新型算法,以解决混凝土骨架点问题。 我们的结果基于一个新的简单的最小遗憾最小化器,即Conic Blackwell Algorithm $ $(CBA$ $ $ ), 达到美元( 1/\ sqrt{T} $ ) 的平均遗憾。 直观地说, 我们的方法将反事实最小化( CFR$ $ $ ) 算法中的其他决定性利益概念概括化为一种简单的算法, 该算法在解决简单x顺序游戏时具有很强的实用性能。 我们展示了如何在简单x 、 $\ ellp} 标准球和 光线性信任区实施 CBA$ $, 我们展示了解决矩阵游戏和分布强大的优化问题的数字实验。 我们的经验结果表明, CBA$ $ 是一个简单的算法, 超越了合成数据和真实数据案例中的当前最先进的方法, 不需要任何步骤大小或其他算参数的选择 。