arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.03033cs.LGstat.ML
收藏

最优多保真度最佳臂识别

Optimal Multi-Fidelity Best-Arm Identification

DEIB, Politecnico di Milano(迪埃布(DEIB),米兰理工学院);Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189-CRIStAL(里尔大学、法国国家科学研究中心、Inria、Centrale Lille、UMR 9189-CRIStAL)

Riccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli

AI总结:

本文针对多保真度最佳臂识别问题,提出紧的下界和基于梯度的渐近最优算法,并揭示每臂最优保真度概念。

摘要:

在赌博机最佳臂识别问题中,算法需要以指定的精度尽快找到具有最高平均奖励的臂。我们研究多保真度最佳臂识别问题,在该问题中,算法可以选择以较低保真度(即较不精确的平均估计)对臂进行采样,从而以较低的成本获取信息。已有多种方法被提出用于解决该问题,但其最优性仍然难以捉摸,尤其是由于识别最佳臂所需总成本的下界较为宽松。我们的第一个贡献是给出了一个紧的、依赖于实例的成本复杂度下界。对下界中涉及的优化问题的研究为设计计算高效的算法提供了新的见解,并引导我们提出一种具有渐近最优成本复杂度的基于梯度的方法。我们在实验中展示了新算法相对于现有方法的优势。我们的理论和实证发现也揭示了一个关于每臂最优保真度的有趣概念。

英文摘要:

In bandit best-arm identification, an algorithm is tasked with finding the arm with highest mean reward with a specified accuracy as fast as possible. We study multi-fidelity best-arm identification, in which the algorithm can choose to sample an arm at a lower fidelity (less accurate mean estimate) for a lower cost. Several methods have been proposed for tackling this problem, but their optimality remain elusive, notably due to loose lower bounds on the total cost needed to identify the best arm. Our first contribution is a tight, instance-dependent lower bound on the cost complexity. The study of the optimization problem featured in the lower bound provides new insights to devise computationally efficient algorithms, and leads us to propose a gradient-based approach with asymptotically optimal cost complexity. We demonstrate the benefits of the new algorithm compared to existing methods in experiments. Our theoretical and empirical findings also shed light on an intriguing concept of optimal fidelity for each arm.

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。

↑