arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01400stat.MLcs.DScs.LG
收藏

基于带噪声预言机的查询高效相关聚类

Query-Efficient Correlation Clustering with Noisy Oracle

CENTAI Institute(CENTAI研究所);Eurecat(欧雷特卡特研究中心);Microsoft Research(微软研究院)

Yuko Kuroki, Atsushi Miyauchi, Francesco Bonchi, Wei Chen

AI总结:

针对相似度计算成本高且带噪的聚类场景,研究者基于组合多臂老虎机纯探索范式提出两种在线学习问题构造,设计了结合采样策略与经典相关聚类近似算法的方案,首次给出底层问题为NP难的该类场景多项式时间算法。

摘要:

我们研究了一种通用聚类场景:待聚类元素共$n$个,目标是尽可能少地向预言机发起查询,该预言机会返回两个元素间加权相似度的带噪声样本。该场景涵盖了相似度函数计算成本高且固有带噪声的众多应用领域。我们基于组合多臂老虎机纯探索(PE-CMAB)范式,提出了两种全新的在线学习问题构造:固定置信度设置与固定预算设置。针对两种设置,我们设计了将采样策略与经典相关聚类近似算法相结合的算法,并研究了其理论保证。我们的研究成果是首个适用于底层离线优化问题为NP难的PE-CMAB场景的多项式时间算法实例。

英文摘要:

We study a general clustering setting in which we have $n$ elements to be clustered, and we aim to perform as few queries as possible to an oracle that returns a noisy sample of the weighted similarity between two elements. Our setting encompasses many application domains in which the similarity function is costly to compute and inherently noisy. We introduce two novel formulations of online learning problems rooted in the paradigm of Pure Exploration in Combinatorial Multi-Armed Bandits (PE-CMAB): fixed confidence and fixed budget settings. For both settings, we design algorithms that combine a sampling strategy with a classic approximation algorithm for correlation clustering and study their theoretical guarantees. Our results are the first examples of polynomial-time algorithms that work for the case of PE-CMAB in which the underlying offline optimization problem is NP-hard.

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。

↑