A Survey of Statistical Network Models
From MaRDI portal
Publication:3569376
DOI10.1561/2200000008zbMath1191.68615DBLPjournals/ftml/Luxburg09arXiv1007.1075OpenAlexW3105761396WikidataQ57408120 ScholiaQ57408120MaRDI QIDQ3569376
Publication date: 18 June 2010
Published in: Foundations and Trends® in Machine Learning (Search for Journal in Brave)
Abstract: A popular method for selecting the number of clusters is based on stability arguments: one chooses the number of clusters such that the corresponding clustering results are "most stable". In recent years, a series of papers has analyzed the behavior of this method from a theoretical point of view. However, the results are very technical and difficult to interpret for non-experts. In this paper we give a high-level overview about the existing literature on clustering stability. In addition to presenting the results in a slightly informal but accessible way, we relate them to each other and discuss their different implications.
Full work available at URL: https://arxiv.org/abs/1007.1075
Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)
Related Items (28)
Estimation of the global mode of a density: minimaxity, adaptation, and computational complexity ⋮ Multicuts and perturb \& MAP for probabilistic graph clustering ⋮ Explaining mixture models through semantic pattern mining and banded matrix visualization ⋮ Divisive clustering of high dimensional data streams ⋮ Modal clustering asymptotics with applications to bandwidth selection ⋮ Optimality-based clustering: an inverse optimization approach ⋮ A statistical view of clustering performance through the theory of \(U\)-processes ⋮ Detecting Lagrangian coherent structures from sparse and noisy trajectory data ⋮ Adjusting the Adjusted Rand Index. A multinomial story ⋮ On the discrepancy between Kleinberg's clustering axioms and \(k\)-means clustering algorithm behavior ⋮ Richness fallacy ⋮ A family of distances for preference-approvals ⋮ Detecting communities in attributed networks through bi-direction penalized clustering and its application ⋮ Unnamed Item ⋮ Bootstrapping estimates of stability for clusters, observations and model selection ⋮ Measuring the stability of spectral clustering ⋮ Probabilistic Correlation Clustering and Image Partitioning Using Perturbed Multicuts ⋮ Banks' business models in the euro area: a cluster analysis in high dimensions ⋮ Clustering stability-based evolutionary K-means ⋮ Clustering under Perturbation Resilience ⋮ Stability estimation for unsupervised clustering: a review ⋮ Riding down the Bay: space-time clustering of ecological trends ⋮ On the Estimation of the Number of Communities for Sparse Networks ⋮ Visualizing non-metric similarities in multiple maps ⋮ Optimal transport, mean partition, and uncertainty assessment in cluster analysis ⋮ Good Clusterings Have Large Volume ⋮ Likelihood Inference for Large Scale Stochastic Blockmodels With Covariates Based on a Divide-and-Conquer Parallelizable Algorithm With Communication ⋮ Unnamed Item
This page was built for publication: A Survey of Statistical Network Models
