论文标题
平滑市场：组织基于梯度的学习者的基本机制
Smooth markets: A basic mechanism for organizing gradient-based learners
论文作者
论文摘要
随着现代机器学习的成功，了解和控制学习算法如何相互作用变得越来越重要。不幸的是，游戏理论的负面结果表明，理解或控制一般的N-玩家游戏几乎没有希望。因此，我们引入了流畅的市场（SM-GAMES），这是一类具有成对零和交互的N玩家游戏。 SM-GAMES将机器学习中的常见设计模式编码为包括（某些）gan，对抗训练和其他近期算法。我们表明，使用一阶方法可以很好地通过分析和优化。
With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact. Unfortunately, negative results from game theory show there is little hope of understanding or controlling general n-player games. We therefore introduce smooth markets (SM-games), a class of n-player games with pairwise zero sum interactions. SM-games codify a common design pattern in machine learning that includes (some) GANs, adversarial training, and other recent algorithms. We show that SM-games are amenable to analysis and optimization using first-order methods.
