For finite integer $d$-cubes, we consider the problem of learning a classification $I$ that respects Pareto domination. The setup is natural in dynamic programming settings. We show that a generalization of the binary search algorithm achieves an optimal $\theta(n^{d-1})$ worst-case run time for $d\geq 2$.

翻译：对于限定整数 $d$- 立方体, 我们考虑学习尊重Pareto 支配权的分类 $I 的问题。 设置在动态程序设置中是自然的。 我们显示, 二进制搜索算法的概括化可以实现$\theta (n ⁇ d-1})$( $d\geq 2) 的最坏情况运行时间 。