arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13684cs.LGcs.AI
收藏

关于相关聚类的稀疏化:在边采样下的近似保证

On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling

Department of Computer Science Iowa State University(计算机科学系爱荷华州立大学)

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

AI总结:

研究通过稀疏化相关聚类算法,在边采样下获得鲁棒的近似保证,证明了伪度量结构对算法可计算性和鲁棒性的重要性。

摘要:

相关聚类(CC)是一种基本的无监督学习原始方法,其最强的基于线性规划(LP)的近似保证需要Θ(n³)个三角不等式约束,规模上是不可行的。我们开始研究CC的稀疏化-近似权衡,询问需要保留LP保证的多少边信息。我们建立了伪度量和一般加权实例之间的结构性二元分化。在积极方面,我们证明了聚类分歧类的VC维恰好为n−1,从而得到最优大小的加法ε-coresets,即~O(n/ε²);证明在任何LP顶点处,最多C(n,2)个三角不等式是活跃的,从而能够实现精确的切割平面求解器;并且证明了一种稀疏化版本的LP-PIVOT,通过三角不等式来推断缺失的LP边际,一旦观察到~Θ(n^{3/2})条边,就能得到一个鲁棒的10/3近似(误差项由可经验计算的imputation-quality统计量Γ_w控制)。在消极方面,我们通过Yao的极小最大原理证明,如果没有伪度量结构,任何观察到o(n)条均匀随机边的算法将导致无界的近似比,证明伪度量条件不仅决定了可计算性,还决定了CC在信息不完整时的鲁棒性。

英文摘要:

Correlation Clustering (CC) is a fundamental unsupervised learning primitive whose strongest LP-based approximation guarantees require $Θ(n^3)$ triangle inequality constraints and are prohibitive at scale. We initiate the study of \emph{sparsification--approximation trade-offs} for CC, asking how much edge information is needed to retain LP-based guarantees. We establish a structural dichotomy between pseudometric and general weighted instances. On the positive side, we prove that the VC dimension of the clustering disagreement class is exactly $n{-}1$, yielding additive $\varepsilon$-coresets of optimal size $\tilde{O}(n/\varepsilon^2)$; that at most $\binom{n}{2}$ triangle inequalities are active at any LP vertex, enabling an exact cutting-plane solver; and that a sparsified variant of LP-PIVOT, which imputes missing LP marginals via triangle inequalities, achieves a robust $\frac{10}{3}$-approximation (up to an additive term controlled by an empirically computable imputation-quality statistic $\overlineΓ_w$) once $\tildeΘ(n^{3/2})$ edges are observed, a threshold we prove is sharp. On the negative side, we show via Yao's minimax principle that without pseudometric structure, any algorithm observing $o(n)$ uniformly random edges incurs an unbounded approximation ratio, demonstrating that the pseudometric condition governs not only tractability but also the robustness of CC to incomplete information.

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。

↑