期刊名称：Electronic Colloquium on Computational Complexity
印刷版ISSN：1433-8092
出版年度：2021
卷号：21
语种：English
出版社：Universität Trier, Lehrstuhl für Theoretische Computer-Forschung
摘要：k-median and k-means are the two most popular objectives for clustering algorithms. Despite intensive effort, a good understanding of the approximability of these objectives, particularly in p-metrics, remains a major open problem. In this paper, we significantly improve upon the hardness of approximation factors known in literature for these objectives in p-metrics. We introduce a new hypothesis called the Johnson Coverage Hypothesis (JCH), which roughly asserts that the well-studied k-max coverage problem on set systems is hard to approximate to a factor greater than 1−e1 , even when the membership graph of the set system is a subgraph of the Johnson graph. We then show that together with generalizations of the embedding techniques introduced by Cohen-Addad and Karthik (FOCS '19), JCH implies hardness of approximation results for k-median and k-means in p-metrics for factors which are close to the ones obtained for general metrics. In particular, assuming JCH we show that it is hard to approximate the k-means objective: Discrete case: To a factor of 3.94 in the 1-metric and to a factor of 1.73 in the 2-metric; this improves upon the previous factor of 1.56 and 1.17 respectively, obtained under the Unique Games Conjecture (UGC). Continuous case: To a factor of 2.10 in the 1-metric and to a factor of 1.36 in the 2-metric; this improves upon the previous factor of 1.07 in the 2-metric obtained under UGC (and to the best of our knowledge, the continuous case of k-means in 1-metric was not previously analyzed in literature). We also obtain similar improvements under JCH for the k-median objective. Additionally, we prove a weak version of JCH using the work of Dinur et al. (SICOMP'05) on Hypergraph Vertex Cover, and recover all the results stated above of Cohen-Addad and Karthik (FOCS '19) to (nearly) the same inapproximability factors but now under the standard NP= P assumption (instead of UGC). Finally, we establish a strong connection between JCH and the long standing open problem of determining the Hypergraph Turan number. We then use this connection to prove improved SDP gaps (over the existing factors in literature) for k-means and k-median objectives.
关键词：Clustering;Hardness of Approximation;k-means;k-median;set cover
