{"id":"https://openalex.org/W7160333384","doi":"https://doi.org/10.48550/arxiv.2605.02836","title":"A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification","display_name":"A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160333384","doi":"https://doi.org/10.48550/arxiv.2605.02836"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.02836","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.02836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021160042","display_name":"Sushovan Majhi","orcid":"https://orcid.org/0000-0001-8689-4321"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Majhi, Sushovan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133219880","display_name":"Atish Mitra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitra, Atish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063657601","display_name":"\u017diga Virk","orcid":"https://orcid.org/0000-0001-9016-011X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Virk, \u017diga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036075177","display_name":"Pramita Bagchi","orcid":"https://orcid.org/0000-0003-1766-2767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bagchi, Pramita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021160042"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4596000015735626},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.3978999853134155},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.39559999108314514},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3869999945163727},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.37220001220703125},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.3702999949455261},{"id":"https://openalex.org/keywords/mahalanobis-distance","display_name":"Mahalanobis distance","score":0.34860000014305115},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.34369999170303345}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6694999933242798},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3684000074863434},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C2776562905","wikidata":"https://www.wikidata.org/wiki/Q306610","display_name":"Hypersphere","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3084999918937683},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2734000086784363},{"id":"https://openalex.org/C62438384","wikidata":"https://www.wikidata.org/wiki/Q331350","display_name":"Simplex","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.02836","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.02836","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"PLACE":[2,172],"(Persistence-Landmark":[3],"Analytic":[4],"Classification":[5],"Engine),":[6],"a":[7,24,28,33,58,104,123,144],"closed-form":[8,29,63,120,145],"pipeline":[9],"for":[10],"classifying":[11],"point":[12],"clouds":[13],"and":[14,32,91,168,180,191,221],"graphs":[15],"through":[16],"their":[17],"persistent-homology":[18],"signatures.":[19],"Three":[20],"quantitative":[21],"guarantees":[22],"--":[23,36],"margin-based":[25],"excess-risk":[26],"rate,":[27],"descriptor-selection":[30],"rule,":[31],"per-prediction":[34,159],"certificate":[35,78],"are":[37],"derived":[38],"from":[39],"training":[40],"labels":[41],"alone,":[42],"with":[43,157],"no":[44,158],"learned":[45],"weights":[46],"or":[47],"held-out":[48,231],"calibration.":[49],"The":[50,111,207],"embedding":[51,92],"sums":[52],"Mitra-Virk":[53],"single-point":[54],"coordinate":[55],"functions":[56],"over":[57],"sparse":[59],"landmark":[60],"grid;":[61],"the":[62,72,97,118,139,149,174,182,214,219,235],"weight":[64],"rule":[65],"$w_k^2":[66],"\\propto":[67],"(d_{k+1}^2":[68],"-":[69],"d_k^2)/R_k^2$":[70],"maximizes":[71],"distortion":[73],"slope":[74],"in":[75,96,161],"Mitra-Virk's":[76],"affine":[77],"under":[79,114],"$\u03bd$-coherence.":[80],"(i)":[81],"An":[82],"$O(kR/(\u0394\\sqrt{m_{\\min}}))$":[83],"margin":[84,113],"bound,":[85],"driven":[86],"by":[87,103],"class-mean":[88],"separation":[89],"$\u0394$":[90],"radius":[93,209],"$R$,":[94],"matched":[95],"sample-starved":[98],"regime":[99],"$m":[100],"\\lesssim":[101],"R/\u0394$":[102],"Le":[105],"Cam":[106],"minimax":[107],"lower":[108],"bound.":[109],"(ii)":[110],"Mahalanobis":[112],"Ledoit-Wolf-shrunk":[115],"covariance":[116],"is":[117,173],"strongest":[119,175,183],"ranker":[121],"on":[122,135,148,178,189,202,211,217,226],"64-descriptor":[124],"chemical-graph":[125],"pool":[126],"(mean":[127],"Spearman":[128],"$\u03c1=":[129],"+0.56$":[130],"across":[131],"11":[132],"benchmarks,":[133],"positive":[134],"10":[136],"of":[137,213,229],"11);":[138],"isotropic":[140],"surrogate":[141],"$\u0394/\\sqrt{\\ell}$":[142],"admits":[143],"selection-consistency":[146],"rate":[147],"homogeneous":[150],"protein/social":[151],"pools.":[152],"(iii)":[153],"A":[154],"training-time-decided":[155],"certificate,":[156],"overhead,":[160],"three":[162],"concrete":[163],"radii":[164],"(Pinelis,":[165],"Gaussian":[166],"plug-in,":[167],"variance-aware":[169],"Pinelis-Bernstein).":[170],"Empirically,":[171],"diagram-based":[176],"method":[177],"Orbit5k":[179],"matches":[181],"topology-based":[184],"baseline":[185],"within":[186],"statistical":[187],"noise":[188],"MUTAG":[190,218],"COX2;":[192],"remaining":[193],"gaps":[194],"fall":[195],"into":[196],"two":[197],"diagnosable":[198],"regimes":[199],"(descriptor":[200],"blindness":[201],"NCI1/NCI109;":[203],"pool-coverage":[204],"limits":[205],"elsewhere).":[206],"Pinelis-Bernstein":[208],"fires":[210],"8":[212],"12":[215],"benchmarks;":[216],"empirical":[220],"population":[222],"nearest-centroid":[223],"rules":[224],"agree":[225],"every":[227],"one":[228],"940":[230],"test":[232],"predictions,":[233],"validating":[234],"certificate's":[236],"mechanism.":[237]},"counts_by_year":[],"updated_date":"2026-05-27T06:14:07.914337","created_date":"2026-05-06T00:00:00"}