Sum-of-norms clustering does not separate nearby balls

• URL: http://arxiv.org/abs/2104.13753v3
• Date: Tue, 14 May 2024 11:12:27 GMT
• Title: Sum-of-norms clustering does not separate nearby balls
• Authors: Alexander Dunlap, Jean-Christophe Mourrat,
• Abstract summary: We show a continuous version of sum-of-norms clustering, where the dataset is replaced by a general measure. We state and prove a local-global characterization of the clustering that seems to be new even in the case of discrete datapoints.
• Score: 49.1574468325115
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sum-of-norms clustering is a popular convexification of $K$-means clustering. We show that, if the dataset is made of a large number of independent random variables distributed according to the uniform measure on the union of two disjoint balls of unit radius, and if the balls are sufficiently close to one another, then sum-of-norms clustering will typically fail to recover the decomposition of the dataset into two clusters. As the dimension tends to infinity, this happens even when the distance between the centers of the two balls is taken to be as large as $2\sqrt{2}$. In order to show this, we introduce and analyze a continuous version of sum-of-norms clustering, where the dataset is replaced by a general measure. In particular, we state and prove a local-global characterization of the clustering that seems to be new even in the case of discrete datapoints.

Related papers

• A Unified Framework for Gradient-based Clustering of Distributed Data [51.904327888475606]
  We develop a family of distributed clustering algorithms that work over networks of users. DGC-$mathcalF_rho$ is specialized to popular clustering losses like $K$-means and Huber loss. We show that consensus fixed points of DGC-$mathcalF_rho$ are equivalent to fixed points of gradient clustering over the full data.
  arXiv  Detail & Related papers  (2024-02-02T10:44:42Z)
• UniForCE: The Unimodality Forest Method for Clustering and Estimation of the Number of Clusters [2.4953699842881605]
  We focus on the concept of unimodality and propose a flexible cluster definition called locally unimodal cluster. A locally unimodal cluster extends for as long as unimodality is locally preserved across pairs of subclusters of the data. We propose the UniForCE method for locally unimodal clustering.
  arXiv  Detail & Related papers  (2023-12-18T16:19:02Z)
• Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model [79.46465138631592]
  We devise an efficient algorithm that recovers clusters using the observed labels. We present Instance-Adaptive Clustering (IAC), the first algorithm whose performance matches these lower bounds both in expectation and with high probability.
  arXiv  Detail & Related papers  (2023-06-18T08:46:06Z)
• Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types [60.45942774425782]
  We introduce anomaly clustering, whose goal is to group data into coherent clusters of anomaly types. This is different from anomaly detection, whose goal is to divide anomalies from normal data. We present a simple yet effective clustering framework using a patch-based pretrained deep embeddings and off-the-shelf clustering methods.
  arXiv  Detail & Related papers  (2021-12-21T23:11:33Z)
• Lattice-Based Methods Surpass Sum-of-Squares in Clustering [98.46302040220395]
  Clustering is a fundamental primitive in unsupervised learning. Recent work has established lower bounds against the class of low-degree methods. We show that, perhaps surprisingly, this particular clustering model textitdoes not exhibit a statistical-to-computational gap.
  arXiv  Detail & Related papers  (2021-12-07T18:50:17Z)
• Local versions of sum-of-norms clustering [77.34726150561087]
  We show that our method can separate arbitrarily close balls in the ball model. We prove a quantitative bound on the error incurred in the clustering of disjoint connected sets.
  arXiv  Detail & Related papers  (2021-09-20T14:45:29Z)
• K-expectiles clustering [0.0]
  We propose a novel partitioning clustering algorithm based on expectiles. We suggest two schemes: fixed $tau$ clustering, and adaptive $tau$ clustering.
  arXiv  Detail & Related papers  (2021-03-16T21:14:56Z)
• Quantizing Multiple Sources to a Common Cluster Center: An Asymptotic Analysis [14.048989759890475]
  We consider quantizing an $Ld$-dimensional sample, which is obtained by concatenating $L$ vectors from datasets of $d$-dimensional vectors, to a $d$-dimensional cluster center. We find a formula for the average performance distortion in the regime where the number of cluster centers are large. In terms of faithfulness to the original (noiseless) dataset, our clustering approach outperforms the naive approach that relies on quantizing the $Ld$-dimensional noisy observation vectors to $Ld$-dimensional centers.
  arXiv  Detail & Related papers  (2020-10-23T17:14:28Z)
• Exact Recovery of Mangled Clusters with Same-Cluster Queries [20.03712152278538]
  We study the cluster recovery problem in the semi-supervised active clustering framework. We design an algorithm that, given $n$ points to be partitioned into $k$ clusters, uses $O(k3 ln k ln n)$ oracle queries and $tildeO(kn + k3)$ time to recover the clustering with zero misclassification error.
  arXiv  Detail & Related papers  (2020-06-08T15:27:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.