arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.03972stat.MLcs.AIcs.LG
收藏

固定预算在最佳臂识别中不比固定置信度难(对数因子范围内)

Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

University of California, Berkeley(加州大学伯克利分校);University of Washington(华盛顿大学);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Kapilan Balagopalan, Yinan Li, Yao Zhao, Tuan Nguyen, Anton Daitche, Houssam Nassif, Kwang-Sung Jun

AI总结:

本文提出元算法FC2FB,将固定置信度算法转化为固定预算算法,证明固定预算的样本复杂度在log因子内不高于固定置信度。

摘要:

最佳臂识别(BAI)问题是交互式机器学习中最基本的问题之一,有两种形式:固定预算设置(FB)和固定置信度设置(FC)。对于具有唯一最佳臂的$K$臂赌博机,两种设置的最优样本复杂度已被确定,且在对数因子内匹配。这引出了一个关于通用的、可能具有结构化的BAI问题的有趣研究问题:FB是否比FC更难,还是相反?在本文中,我们证明FB在对数因子内并不比FC难。我们通过构造性方式做到这一点:我们提出了一种名为FC2FB(固定置信度到固定预算)的新算法,这是一种元算法,它接收一个FC算法$\mathcal{A}$并将其转化为FB算法。我们证明FC2FB的样本复杂度与$\mathcal{A}$的样本复杂度在对数因子内匹配。这意味着最优FC样本复杂度是FB最优样本复杂度的一个上界(在对数因子内)。我们的结果不仅揭示了FB和FC之间的基本关系,而且具有重要含义:FC2FB与现有最先进的FC算法相结合,可以改善许多FB问题的样本复杂度。

英文摘要:

The best-arm identification (BAI) problem is one of the most fundamental problems in interactive machine learning, which has two flavors: the fixed-budget setting (FB) and the fixed-confidence setting (FC). For $K$-armed bandits with a unique best arm, the optimal sample complexities for both settings have been settled down, and they match up to logarithmic factors. This prompts an interesting research question about the generic, potentially structured BAI problems: is FB harder than FC or the other way around? In this paper, we show that FB is no harder than FC up to logarithmic factors. We do this constructively: we propose a novel algorithm called FC2FB (fixed confidence to fixed budget), which is a meta algorithm that takes in an FC algorithm $\mathcal{A}$ and turn it into an FB algorithm. We prove that FC2FB enjoys a sample complexity that matches, up to logarithmic factors, that of the sample complexity of $\mathcal{A}$. This means that the optimal FC sample complexity is an upper bound of the optimal FB sample complexity up to logarithmic factors. Our result not only reveals a fundamental relationship between FB and FC, but also has a significant implication: FC2FB combined with existing state-of-the-art FC algorithms leads to improved sample complexity for a number of FB problems.

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。

↑