Skip to main content
QUICK REVIEW

[论文解读] Learning Optimal Search Algorithms from Data.

Shuchi Chawla, Evangelia Gergatsouli|arXiv (Cornell University)|Nov 5, 2019
Machine Learning and Algorithms被引用 4
一句话总结

本文提出一种数据驱动框架,用于学习部分自适应搜索算法,以最小化在未知代价的非结构化空间中的解代价与搜索时间之和。结果表明,此类策略可从样本中高效学习,并近似非自适应与完全自适应策略,即使后者的学习在计算上极为困难。

ABSTRACT

Classical algorithm design is geared towards worst case instances and fails to exploit structure that may be present in typical instances. Is it possible to learn this structure from examples and exploit it algorithmically? We study this question in the simplest algorithmic context -- search for a cheap solution within an unstructured space. This setting captures, for example, search for a short path to drive to work when only some routes may ever be relevant to consider, or shopping online when there may only be a handful of stores that offer the best prices. We propose a framework for learning optimal search algorithms from data that captures the tradeoff between the cost of the solution and the time to find it. We consider a setting with $n$ alternatives each having an unknown cost that can be revealed one at a time. Given sample access to the distribution of the costs, our goal is to learn an algorithm that minimizes the expected sum of the cost of the chosen alternative and the total time to find it. Algorithms for this problem fall into three different classes, non-adaptive which always query a fixed set of alternatives, partially-adaptive that query alternatives in a fixed order until they decide to stop and fully-adaptive that choose the next query based on the costs they've seen. While approximately optimal fully-adaptive strategies cannot be learned efficiently, our main result is that it is possible to learn a partially-adaptive strategy that approximates the best non-adaptive and partially-adaptive strategies efficiently both in terms of samples and computation. We extend our results to settings where multiple alternatives must be chosen and study the case where any $k$ alternatives are feasible and the case where the alternatives must form a matroid base e.g. picking a minimum cost spanning tree.

研究动机与目标

  • 解决经典算法设计的局限性,即仅关注最坏情况性能,而忽略典型实例的结构特征。
  • 设计一种基于学习的方法,利用典型实例中的统计结构以提升搜索效率。
  • 最小化在未知代价的非结构化搜索空间中解代价与搜索时间的期望总和。
  • 开发一种方法,高效学习近似最优非自适应与完全自适应策略的部分自适应策略。
  • 将框架扩展至多候选场景,包括基于拟阵的约束(如最小生成树)。

提出的方法

  • 该框架将搜索建模为一个序列决策问题,其中各备选方案的代价逐个被揭示。
  • 利用对代价分布的样本访问,学习一个固定查询顺序并结合提前停止机制,形成部分自适应策略。
  • 学习过程通过在候选策略上进行经验风险最小化,优化解代价与求解时间之间的权衡。
  • 证明了近似最优的完全自适应策略无法被高效学习,从而为聚焦于部分自适应策略提供了理论依据。
  • 该方法采用样本高效算法,学习能近似最优非自适应与部分自适应策略的策略。
  • 该方法可推广至需选择多个可行备选方案的场景,包括拟阵基与k-可行选择。

实验结果

研究问题

  • RQ1我们能否从数据中学习利用典型实例结构而非最坏情况假设的搜索算法?
  • RQ2是否可能学习部分自适应策略,以高效近似最优的非自适应与完全自适应策略?
  • RQ3在非结构化搜索空间中,学习此类策略的样本复杂度与计算复杂度是多少?
  • RQ4所学习的部分自适应策略的性能保证与非自适应及完全自适应策略相比如何?
  • RQ5该框架能否扩展至具有组合约束(如拟阵基)的多候选选择问题?

主要发现

  • 部分自适应策略可从样本中高效学习,并近似最优的非自适应与部分自适应策略。
  • 近似最优的完全自适应策略无法被高效学习,揭示了可学习性的根本限制。
  • 所提方法在学习兼顾解代价与搜索时间的策略时,实现了样本效率与计算效率。
  • 该框架成功扩展至多候选场景,包括任意k个备选方案均可行,或备选方案必须构成拟阵基的情况。
  • 所学策略通过基于观测代价的动态自适应,显著优于非自适应方法,从而降低了期望总代价。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。