从样本中学习子模排序
Learning Submodular Sequencing from Samples
AI总结:
针对仅有样本而未知效用函数的序列子模最大化问题,提出利用两阶段均匀分布的多项式样本学习排序,并取得依赖子模函数曲率的近似保证。
摘要:
本文研究序列子模最大化问题:在一个序列中选择并排列物品,以优化某个复合子模函数。与以往大多数假设可以访问效用函数的工作不同,我们假设只给定一组样本。每个样本包含一个随机的物品序列及其相关效用。我们提出一种算法,在给定从两阶段均匀分布中抽取的多项式数量样本的情况下,可获得取决于各个子模函数曲率的近似比。我们的结果适用于多种现实场景,例如在线零售平台中的商品排序,在这些场景中通常不可能获得效用函数的完整知识。我们的算法在此类情境下给出了经验上有用的解决方案,从而证明有限数据在排序任务中可能非常有用。从技术角度看,我们的结果扩展了以往关于“从样本中优化”的工作,将其从优化集合函数推广到依赖序列的函数。
英文摘要:
This paper addresses the problem of sequential submodular maximization: selecting and ranking items in a sequence to optimize some composite submodular function. In contrast to most of the previous works, which assume access to the utility function, we assume that we are given only a set of samples. Each sample includes a random sequence of items and its associated utility. We present an algorithm that, given polynomially many samples drawn from a two-stage uniform distribution, achieves an approximation ratio dependent on the curvature of individual submodular functions. Our results apply in a wide variety of real-world scenarios, such as ranking products in online retail platforms, where complete knowledge of the utility function is often impossible to obtain. Our algorithm gives an empirically useful solution in such contexts, thus proving that limited data can be of great use in sequencing tasks. From a technical perspective, our results extend prior work on ``optimization from samples'' by generalizing from optimizing a set function to a sequence-dependent function.
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。