{"id":"https://openalex.org/W7160880337","doi":"https://doi.org/10.48550/arxiv.2605.06959","title":"Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions","display_name":"Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160880337","doi":"https://doi.org/10.48550/arxiv.2605.06959"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.06959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06959","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.06959","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112933174","display_name":"H. Kanj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanj, Haitham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033729252","display_name":"Kiryung Lee","orcid":"https://orcid.org/0000-0003-1909-6041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Kiryung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6236000061035156,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6236000061035156,"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/T10136","display_name":"Statistical Methods and Inference","score":0.18039999902248383,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.11289999634027481,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.7264999747276306},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.65420001745224},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5248000025749207},{"id":"https://openalex.org/keywords/piecewise-linear-function","display_name":"Piecewise linear function","score":0.5199000239372253},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5120999813079834},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4876999855041504},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.4634000062942505},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.45350000262260437},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4458000063896179}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.8281000256538391},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7264999747276306},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.65420001745224},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5625},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C17095337","wikidata":"https://www.wikidata.org/wiki/Q2375229","display_name":"Piecewise linear function","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5120999813079834},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.4634000062942505},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C74127309","wikidata":"https://www.wikidata.org/wiki/Q3455886","display_name":"Nonparametric regression","level":3,"score":0.4374000132083893},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.06959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06959","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.06959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06959","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":"Preprint"},"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":{"This":[0,88],"paper":[1],"presents":[2],"a":[3,57,101],"parametric":[4],"solution":[5],"to":[6,75,105,110,128],"piecewise":[7,27],"linear":[8,28],"regression":[9],"through":[10],"the":[11,21,24,31,63,85,96,117,129],"Adaptive":[12],"Block":[13],"Gradient":[14],"Descent":[15],"(ABGD)":[16],"algorithm.":[17],"The":[18],"heart":[19],"of":[20,26,33,66],"method":[22],"is":[23,44,103],"parametrization":[25],"functions":[29],"as":[30],"difference":[32],"max-affine":[34,67],"(DoMA)":[35],"functions.":[36,68],"A":[37],"non-asymptotic":[38],"local":[39],"convergence":[40],"analysis":[41],"for":[42,62,120],"ABGD":[43,72],"provided":[45],"under":[46],"sub-Gaussian":[47],"covariate":[48],"and":[49],"noise":[50,86],"distributions.":[51],"To":[52],"initialize":[53],"ABGD,":[54],"we":[55],"adapt":[56],"prior":[58],"algorithm":[59],"originally":[60],"developed":[61],"simpler":[64],"setting":[65],"When":[69],"suitably":[70],"initialized,":[71],"converges":[73],"linearly":[74],"an":[76],"$\u03b5$-accurate":[77],"estimate":[78],"given":[79,92],"$\\tilde{\\mathcal{O}}(d\\max(\u03c3_z/\u03b5,1)^2)$":[80],"observations":[81],"where":[82],"$\u03c3_z^2$":[83],"denotes":[84],"variance.":[87],"implies":[89],"exact":[90],"recovery":[91],"$\\tilde{\\mathcal{O}}(d)$":[93],"samples":[94],"in":[95],"noiseless":[97],"case.":[98],"Also,":[99],"such":[100],"rate":[102],"shown":[104],"be":[106],"minimax":[107],"optimal":[108],"up":[109],"logarithmic":[111],"factors.":[112],"Synthetic":[113],"numerical":[114],"results":[115],"corroborate":[116],"theoretical":[118],"guarantees":[119],"ABGD.":[121],"We":[122],"also":[123],"observe":[124],"competitive":[125],"performance":[126],"compared":[127],"state-of-the-art":[130],"methods":[131],"on":[132],"real-world":[133],"datasets.":[134]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}