arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05690cs.LGcs.ITmath.IT
收藏

通过成对观测实现近似最优的主动聚类

Almost Asymptotically Optimal Active Clustering Through Pairwise Observations

National University of Singapore(国立新加坡大学);Indian Institute of Technology Hyderabad(印度海得拉巴理工学院);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Rachel S. Y. Teo, P. N. Karthik, Ramya Korlakai Vinayak, Vincent Y. F. Tan

AI总结:

通过成对观测实现近似最优的主动聚类,利用测度变化技术建立查询次数下界,并设计渐近最优算法。

摘要:

我们提出了一种新的分析框架,用于利用噪声和主动收集的响应将M个项目划分为未知数量K个不同的群体。在每个时间步,一个代理被允许查询成对的项目并观察带抵制二进制反馈。如果成对的项目属于同一(resp.不同)簇,观察到的反馈为1的概率是p>1/2(resp. q<1/2)。利用普遍的测度变化技术,我们建立了预期查询次数的基本下界,以实现所需的置信度在聚类准确性中,以sup-inf优化问题的形式表述。基于这一理论基础,我们设计了一个渐近最优的算法,其中停止准则涉及内部下界的经验版本——广义似然比(GLR)统计量——与一个阈值进行比较。我们开发了一个计算上可行的GLR统计量的变种,并证明其性能与下界之间的差距可以被准确地经验估计,并且保持在下界常数倍以内。

英文摘要:

We propose a new analysis framework for clustering $M$ items into an unknown number of $K$ distinct groups using noisy and actively collected responses. At each time step, an agent is allowed to query pairs of items and observe bandit binary feedback. If the pair of items belongs to the same (resp.\ different) cluster, the observed feedback is $1$ with probability $p>1/2$ (resp.\ $q<1/2$). Leveraging the ubiquitous change-of-measure technique, we establish a fundamental lower bound on the expected number of queries needed to achieve a desired confidence in the clustering accuracy, formulated as a sup-inf optimization problem. Building on this theoretical foundation, we design an asymptotically optimal algorithm in which the stopping criterion involves an empirical version of the inner infimum -- the Generalized Likelihood Ratio (GLR) statistic -- being compared to a threshold. We develop a computationally feasible variant of the GLR statistic and show that its performance gap to the lower bound can be accurately empirically estimated and remains within a constant multiple of the lower 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。

↑