The main topic of this paper are algorithms for computing Nash equilibria. We cast our particular methods as instances of a general algorithmic abstraction, namely, a method we call {\em algorithmic boosting}, which is also relevant to other fixed-point computation problems. Algorithmic boosting is the principle of computing fixed points by taking (long-run) averages of iterated maps and it is a generalization of exponentiation. We first define our method in the setting of nonlinear maps. Secondly, we restrict attention to convergent linear maps (for computing dominant eigenvectors, for example, in the PageRank algorithm) and show that our algorithmic boosting method can set in motion {\em exponential speedups in the convergence rate}. Thirdly, we show that algorithmic boosting can convert a (weak) non-convergent iterator to a (strong) convergent one. We also consider a {\em variational approach} to algorithmic boosting providing tools to convert a non-convergent continuous flow to a convergent one. Then, by embedding the construction of averages in the design of the iterated map, we constructively prove the existence of Nash equilibria (and, therefore, Brouwer fixed points). We then discuss implementations of averaging and exponentiation, an important matter even for the scalar case. We finally discuss a relationship between dominant (PageRank) eigenvectors and Nash equilibria.
A scalable stage-wise approach to large-margin multi-class loss based boosting
Australian Center for Visual Technologies(澳大利亚视觉技术中心);The University of Adelaide(阿德莱德大学)
我们提出了一个可扩展的和有效的分类模型,训练多类助推多类分类问题。Shen和Hao在直接最大化多类边际的意义上引入了多类提升的直接公式[C. Shen和Z. Hao,“A direct formulation for totally-corrective multi-class boosting”,in Proc. IEEE Conf. Comp. Vis.帕特恩,2011年]。他们的方法的主要问题是它的高计算复杂性的训练,这阻碍了其在现实世界中的问题的应用。在这项工作中,我们提出了一个可扩展的和简单的阶段式多类提升方法,它也直接最大化的多类边缘。我们的方法提供了几个优点:1)它是简单和计算效率的训练。该方法在不牺牲分类精度的情况下,可以将训练时间加快两个数量级以上。2)与传统的AdaBoost一样,它对参数的选择不太敏感,并且经验上表现出出色的泛化性能。具有挑战性的多类机器学习和视觉任务的实验结果表明,所提出的方法大大提高了收敛速度和准确性的最终视觉检测器相比,现有的多类提升没有额外的计算成本。