arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.09963cs.LGcs.DS
收藏

启发式函数贪婪最佳优先和A* 搜索的样本复杂度

Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search

The University of Tokyo(东京大学)

Shinsaku Sakaue, Taihei Oki

摘要:

贪婪最佳优先搜索(GBFS)和A* 搜索(A*)是在大型图上进行路径查找的流行算法。两者都使用所谓的启发式函数,该函数估计顶点与目标的距离。虽然启发式函数已经使用领域知识手工制作,但最近的研究表明,从数据中学习启发式函数在许多应用中是有效的。受这种新兴方法的启发,我们研究了GBFS和A* 学习启发式函数的样本复杂性。我们建立在最近的框架称为\textit{data-driven algorithm design}和评估的\textit{pseudo-dimension}的一类效用函数,衡量参数化算法的性能。假设一个顶点集的大小$n$是固定的,我们提出了$\mathrm{O}(n\lg n)$和$\mathrm{O}(n^2\lg n)$上界的伪尺寸GBFS和A*,分别由启发式函数值参数化。如果每个顶点的度至多为$d$,则A* 的上界可以改进为$\mathrm{O}(n^2\lg d)$,如果边权重是以$\mathrm{poly}(n)$为界的整数,则A* 的上界可以改进为$\mathrm{O}(n \lg n)$。我们还给出了GBFS和A* 的$Ω(n)$下界,这意味着在整数权条件下,我们的GBFS和A* 的界紧到一个$\lg n$因子。最后,我们讨论的情况下,A* 的性能是衡量的次优性,并表明,我们有时可以得到一个更好的保证,通过结合参数依赖的最坏情况下的样本复杂性界。

英文摘要:

Greedy best-first search (GBFS) and A* search (A*) are popular algorithms for path-finding on large graphs. Both use so-called heuristic functions, which estimate how close a vertex is to the goal. While heuristic functions have been handcrafted using domain knowledge, recent studies demonstrate that learning heuristic functions from data is effective in many applications. Motivated by this emerging approach, we study the sample complexity of learning heuristic functions for GBFS and A*. We build on a recent framework called \textit{data-driven algorithm design} and evaluate the \textit{pseudo-dimension} of a class of utility functions that measure the performance of parameterized algorithms. Assuming that a vertex set of size $n$ is fixed, we present $\mathrm{O}(n\lg n)$ and $\mathrm{O}(n^2\lg n)$ upper bounds on the pseudo-dimensions for GBFS and A*, respectively, parameterized by heuristic function values. The upper bound for A* can be improved to $\mathrm{O}(n^2\lg d)$ if every vertex has a degree of at most $d$ and to $\mathrm{O}(n \lg n)$ if edge weights are integers bounded by $\mathrm{poly}(n)$. We also give $Ω(n)$ lower bounds for GBFS and A*, which imply that our bounds for GBFS and A* under the integer-weight condition are tight up to a $\lg n$ factor. Finally, we discuss a case where the performance of A* is measured by the suboptimality and show that we can sometimes obtain a better guarantee by combining a parameter-dependent worst-case bound with a sample complexity bound.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑