We prove the familiar Lazy Online Gradient Descent algorithm is universal on polytope domains. That means it gets $O(1)$ pseudo-regret against i.i.d opponents, while simultaneously achieving the well-known $O(\sqrt N)$ worst-case regret bound. For comparison the bulk of the literature focuses on variants of the Hedge (exponential weights) algorithm on the simplex. These can in principle be lifted to general polytopes; however the process is computationally unfeasible for many important classes where the number of vertices grows quickly with the dimension. The lifting procedure also ignores any Euclidean bounds on the cost vectors, and can create extra factors of dimension in the pseudo-regret bound. Gradient Descent is simpler than the handful of purpose-built algorithms for polytopes in the literature, and works in a broader setting. In particular existing algorithms assume the optimiser is unique, while our bound allows for several optimal vertices.
翻译:我们证明熟悉的Lazy在线梯子源代码算法在聚点域是普遍性的。 这意味着它能对i.d对手获得1美元(1美元)的假正反正值, 同时能同时达到众所周知的$O(sqrt N)$最坏的偏差。 比较而言, 大部分文献集中在简单x 上的隐蔽算法的变体( 显性重量) 。 这些在原则上可以被提升到普通的多面体; 但是对于许多重要类别来说, 这一过程在计算上是行不通的, 因为其中的顶点随着维度的大小而迅速增长。 提升程序也忽略了成本矢量上的任何 Euclidean 边框, 并且可以在伪正负的矢量上创造额外的维度因素 。 梯子比文献中用于多面的少数目的算法( 显性算法) 简单得多, 并在更宽的环境下工作。 特别是现有的算法假设选法是独一无二的, 而我们的界限允许有几种最佳的顶点 。