Clustering by non-parametric smoothing

Clustering by non-parametric smoothing | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Clustering by non-parametric smoothing David Hofmeyr This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7580570/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract A novel formulation of the clustering problem is introduced in which the task is expressed as an estimation problem, where the object to be estimated is a function which maps a point to its distribution of cluster membership. Unlike existing approaches which implicitly estimate such a function, like Gaussian Mixture Models (GMMs), the proposed approach bypasses any explicit modelling assumptions and exploits the flexible estimation potential of non-parametric smoothing. An intuitive approach for selecting the tuning parameters governing estimation is provided, which allows the proposed method to automatically determine both anappropriate level of flexibility and also the number of clusters to extract from a given data set. Experiments on a large collection of publicly available data sets are used to document the strong performance of the proposed approach, in comparison with relevant benchmarks from the literature. R code to implement the proposed approach is available from https://github.com/DavidHofmeyr/CNS . Cluster analysis automatic clustering k-nearest neighbours Markov chain clustering Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 13 Oct, 2025 Reviews received at journal 13 Oct, 2025 Reviews received at journal 08 Oct, 2025 Reviewers agreed at journal 21 Sep, 2025 Reviewers agreed at journal 21 Sep, 2025 Reviewers invited by journal 21 Sep, 2025 Editor assigned by journal 12 Sep, 2025 Submission checks completed at journal 11 Sep, 2025 First submitted to journal 10 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7580570","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":519684636,"identity":"027ea74e-b3b6-42f8-a058-c87f5e0b5d60","order_by":0,"name":"David Hofmeyr","email":"data:image/png;base64,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","orcid":"","institution":"Lancaster University","correspondingAuthor":true,"prefix":"","firstName":"David","middleName":"","lastName":"Hofmeyr","suffix":""}],"badges":[],"createdAt":"2025-09-10 08:38:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7580570/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7580570/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92619047,"identity":"b30d931f-00a5-4f09-8654-121adb9f9b1f","added_by":"auto","created_at":"2025-10-01 18:28:08","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":311324,"visible":true,"origin":"","legend":"","description":"","filename":"CNSSTCO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7580570/v1/d51c5ce35efce2abdb695c6b.pdf"},{"id":92619172,"identity":"7b2c3c44-df48-449e-9ba0-a7205f4bc3d8","added_by":"auto","created_at":"2025-10-01 18:36:08","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2894,"visible":true,"origin":"","legend":"","description":"","filename":"278b793ca5994276a78d13be2eae61e0.json","url":"https://assets-eu.researchsquare.com/files/rs-7580570/v1/9cac5f7d78d1a6734aaec40d.json"},{"id":92619173,"identity":"dd44d32e-6a16-44c9-9de8-c5d924459f41","added_by":"auto","created_at":"2025-10-01 18:36:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":289508,"visible":true,"origin":"","legend":"","description":"","filename":"CNSSTCO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7580570/v1_covered_2d35e338-a1be-404d-acf0-98ee1c376b7e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Clustering by non-parametric smoothing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"statistics-and-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"stco","sideBox":"Learn more about [Statistics and Computing](http://link.springer.com/journal/11222)","snPcode":"11222","submissionUrl":"https://submission.nature.com/new-submission/11222/3","title":"Statistics and Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Cluster analysis, automatic clustering, k-nearest neighbours, Markov chain clustering","lastPublishedDoi":"10.21203/rs.3.rs-7580570/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7580570/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"A novel formulation of the clustering problem is introduced in which the task is expressed as an estimation problem, where the object to be estimated is a function which maps a point to its distribution of cluster membership. Unlike existing approaches which implicitly estimate such a function, like Gaussian Mixture Models (GMMs), the proposed approach bypasses any explicit modelling assumptions and exploits the flexible estimation potential of non-parametric smoothing. An intuitive approach for selecting the tuning parameters governing estimation is provided, which allows the proposed method to automatically determine both anappropriate level of flexibility and also the number of clusters to extract from a given data set. Experiments on a large collection of publicly available data sets are used to document the strong performance of the proposed approach, in comparison with relevant benchmarks from the literature. R code to implement the proposed approach is available from https://github.com/DavidHofmeyr/CNS.","manuscriptTitle":"Clustering by non-parametric smoothing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-01 18:28:03","doi":"10.21203/rs.3.rs-7580570/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-14T00:44:41+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-13T05:49:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-08T15:10:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"154615129895375745981530961865768968276","date":"2025-09-21T21:02:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"178065489936853371498382384656593588063","date":"2025-09-21T20:12:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-21T19:56:43+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-12T04:37:01+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-11T06:03:19+00:00","index":"","fulltext":""},{"type":"submitted","content":"Statistics and Computing","date":"2025-09-10T08:22:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"statistics-and-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"stco","sideBox":"Learn more about [Statistics and Computing](http://link.springer.com/journal/11222)","snPcode":"11222","submissionUrl":"https://submission.nature.com/new-submission/11222/3","title":"Statistics and Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a9f99bd8-82c2-4ede-82bb-17a048f91bb1","owner":[],"postedDate":"October 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-14T18:08:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-01 18:28:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7580570","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7580570","identity":"rs-7580570","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}