The Condition-Number Principle for Prototype Clustering

• URL: http://arxiv.org/abs/2604.07744v1
• Date: Thu, 09 Apr 2026 03:03:01 GMT
• Title: The Condition-Number Principle for Prototype Clustering
• Abstract summary: We develop a geometric framework that links objective accuracy to structural recovery in prototype-based clustering.<n>We define a clustering condition number that compares within-cluster scale to the minimum loss increase required to move a point across a cluster boundary.<n>We show that errors concentrate near cluster boundaries and that sufficiently deep cluster cores are recovered exactly under strengthened local margins.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We develop a geometric framework that links objective accuracy to structural recovery in prototype-based clustering. The analysis is algorithm-agnostic and applies to a broad class of admissible loss functions. We define a clustering condition number that compares within-cluster scale to the minimum loss increase required to move a point across a cluster boundary. When this quantity is small, any solution with a small suboptimality gap must also have a small misclassification error relative to a benchmark partition. The framework also clarifies a fundamental trade-off between robustness and sensitivity to cluster imbalance, leading to sharp phase transitions for exact recovery under different objectives. The guarantees are deterministic and non-asymptotic, and they separate the role of algorithmic accuracy from the intrinsic geometric difficulty of the instance. We further show that errors concentrate near cluster boundaries and that sufficiently deep cluster cores are recovered exactly under strengthened local margins. Together, these results provide a geometric principle for interpreting low objective values as reliable evidence of meaningful clustering structure.

Related papers

• Seed-Guided Semi-Supervised Clustering by A-Contrario Anomaly Detection [0.0]
  This paper introduces a semi-supervised clustering framework grounded in the statistical duality between grouping principles and anomaly detection.<n>We define a cluster as a maximal subset of data points containing no anomalies relative to a null hypothesis of uniform randomness.<n>We evaluate the method on synthetic and real-world benchmarks, including image and text datasets represented through raw, linear-reduced, and neighbourhood-exclusion embeddings.
  arXiv  Detail & Related papers  (2026-06-17T09:08:02Z)
• K*-Means: A Parameter-free Clustering Algorithm [55.20132267309382]
  k*-means is a novel clustering algorithm that eliminates the need to set k or any other parameters.<n>It uses the minimum description length principle to automatically determine the optimal number of clusters, k*, by splitting and merging clusters.<n>We prove that k*-means is guaranteed to converge and demonstrate experimentally that it significantly outperforms existing methods in scenarios where k is unknown.
  arXiv  Detail & Related papers  (2025-05-17T08:41:07Z)
• Hierarchical and Density-based Causal Clustering [6.082022112101251]
  We propose plug-in estimators that are simple and readily implementable using off-the-shelf algorithms. We go on to study their rate of convergence, and show that the additional cost of causal clustering is essentially the estimation error of the outcome regression functions.
  arXiv  Detail & Related papers  (2024-11-02T14:01:04Z)
• Proportional Fairness in Non-Centroid Clustering [34.91134564352282]
  We revisit the recently developed framework of proportionally fair clustering, where the goal is to provide group fairness guarantees. We expand the framework to non-centroid clustering, where the loss of an agent is a function of the other agents in its cluster. We show that the best approximation we are able to establish, using an adaptation of the GreedyCapture algorithm, is unappealing for a natural loss function.
  arXiv  Detail & Related papers  (2024-10-30T17:53:49Z)
• Self-Supervised Graph Embedding Clustering [70.36328717683297]
  K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. We propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework.
  arXiv  Detail & Related papers  (2024-09-24T08:59:51Z)
• Dirichlet Process-based Robust Clustering using the Median-of-Means Estimator [16.774378814288806]
  We propose an efficient and automatic clustering technique by integrating the strengths of model-based and centroid-based methodologies.<n>Our method mitigates the effect of noise on the quality of clustering; while at the same time, estimates the number of clusters.
  arXiv  Detail & Related papers  (2023-11-26T19:01:15Z)
• Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model [85.51611950757643]
  We propose IAC (Instance-Adaptive Clustering), the first algorithm whose performance matches the instance-specific lower bounds both in expectation and with high probability.<n>IAC maintains an overall computational complexity of $ mathcalO(n, textpolylog(n) $, making it scalable and practical for large-scale problems.
  arXiv  Detail & Related papers  (2023-06-18T08:46:06Z)
• Perfect Spectral Clustering with Discrete Covariates [68.8204255655161]
  We propose a spectral algorithm that achieves perfect clustering with high probability on a class of large, sparse networks. Our method is the first to offer a guarantee of consistent latent structure recovery using spectral clustering.
  arXiv  Detail & Related papers  (2022-05-17T01:41:06Z)
• Gradient Based Clustering [72.15857783681658]
  We propose a general approach for distance based clustering, using the gradient of the cost function that measures clustering quality. The approach is an iterative two step procedure (alternating between cluster assignment and cluster center updates) and is applicable to a wide range of functions.
  arXiv  Detail & Related papers  (2022-02-01T19:31:15Z)
• Clustering to the Fewest Clusters Under Intra-Cluster Dissimilarity Constraints [0.0]
  equiwide clustering relies neither on density nor on a predefined number of expected classes, but on a dissimilarity threshold. We review and evaluate suitable clustering algorithms to identify trade-offs between the various practical solutions for this clustering problem.
  arXiv  Detail & Related papers  (2021-09-28T12:02:18Z)
• Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
  Existing scalable hierarchical clustering methods sacrifice quality for speed. We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
  arXiv  Detail & Related papers  (2020-10-22T15:58:35Z)

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.