{"id":"https://openalex.org/W7164056877","doi":"https://doi.org/10.48550/arxiv.2606.09382","title":"Consecutive Support Matching Induced Parameter Tuning Accelerates Momentum Iterative Hard Thresholding","display_name":"Consecutive Support Matching Induced Parameter Tuning Accelerates Momentum Iterative Hard Thresholding","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164056877","doi":"https://doi.org/10.48550/arxiv.2606.09382"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09382","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.09382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138210991","display_name":"Samrat Mukhopadhyay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukhopadhyay, Samrat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061811026","display_name":"Debasmita Mukherjee","orcid":"https://orcid.org/0000-0003-4950-0631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukherjee, Debasmita","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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9650999903678894,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9650999903678894,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.007799999788403511,"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/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.6039000153541565},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5813999772071838},{"id":"https://openalex.org/keywords/hinge-loss","display_name":"Hinge loss","score":0.5773000121116638},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5151000022888184},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.47780001163482666},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.413100004196167},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.3935000002384186},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.3666999936103821}],"concepts":[{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5878000259399414},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5813999772071838},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.5773000121116638},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.492900013923645},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4043000042438507},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.3935000002384186},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C17902559","wikidata":"https://www.wikidata.org/wiki/Q17099734","display_name":"Restricted isometry property","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C163415756","wikidata":"https://www.wikidata.org/wiki/Q126473","display_name":"Contraction (grammar)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09382","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.09382","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Momentum-based":[0],"acceleration":[1],"of":[2,73,133,151,180],"iterative":[3,223],"hard":[4,36],"thresholding":[5],"(IHT)":[6],"can":[7],"dramatically":[8],"speed":[9],"up":[10,137],"sparse":[11,224],"signal":[12],"recovery":[13,135,225,230],"from":[14],"linear":[15,131],"measurements,":[16],"but":[17],"its":[18],"effectiveness":[19],"hinges":[20],"on":[21,148,177,209],"careful":[22],"parameter":[23],"tuning":[24],"--":[25],"a":[26,51,80,120,130,139,167,189],"task":[27],"complicated":[28],"by":[29],"the":[30,57,66,70,74,87,125,134,149,156,160,178,183,196,202,229],"frequent":[31],"support":[32,75,104,111],"changes":[33],"inherent":[34],"to":[35,86,96,138,154,195],"thresholding.":[37],"We":[38,200],"propose":[39],"CosMIHT(Consecutive":[40],"Support":[41],"Matching":[42],"Induced":[43],"Momentum":[44],"IHT),":[45],"which":[46],"resolves":[47],"this":[48],"difficulty":[49],"through":[50],"simple":[52],"adaptive":[53],"rule:":[54],"start":[55],"with":[56,166,186,205],"conservative":[58],"parameters":[59],"and":[60,84,106,142,212],"whenever":[61],"two":[62],"consecutive":[63],"iterates":[64],"share":[65],"same":[67],"support,":[68],"estimate":[69],"extreme":[71],"eigenvalues":[72],"restricted":[76,115],"Gram":[77],"matrix":[78],"via":[79],"lightweight":[81],"power":[82,170,181],"method":[83,171],"switch":[85],"corresponding":[88],"optimal":[89],"heavy-ball":[90],"parameters.":[91],"This":[92],"mechanism":[93],"allows":[94],"CosMIHT":[95,217],"automatically":[97],"interpolate":[98],"between":[99],"cautious":[100],"MIHT-like":[101],"behavior":[102],"during":[103],"discovery":[105],"near-optimal":[107,190],"accelerated":[108,191],"convergence":[109,122,192,220],"after":[110],"identification.":[112],"Under":[113],"standard":[114],"isometry":[116],"assumptions,":[117],"we":[118,128,163],"develop":[119],"two-phase":[121],"theory.":[123],"In":[124,159],"\\emph{wandering":[126],"phase},":[127],"establish":[129,164],"contraction":[132],"error":[136],"noise":[140],"floor":[141],"derive":[143],"an":[144],"explicit":[145],"upper":[146],"bound":[147],"number":[150,179],"iterations":[152],"required":[153],"identify":[155],"correct":[157],"support.":[158],"\\emph{lock-in}":[161],"phase,":[162],"that,":[165],"randomly":[168],"initialized":[169],"based":[172],"eigenvalue":[173],"estimates":[174],"that":[175,216],"depend":[176],"iterations,":[182],"algorithm":[184],"enjoys,":[185],"high":[187],"probability,":[188],"rate":[193],"akin":[194],"heavy":[197],"ball":[198],"method.":[199],"corroborate":[201],"theoretical":[203],"findings":[204],"extensive":[206],"numerical":[207],"experiments":[208],"both":[210],"noiseless":[211],"noisy":[213],"measurements":[214],"demonstrating":[215],"achieves":[218],"faster":[219],"than":[221],"state-of-the-art":[222],"techniques":[226],"without":[227],"compromising":[228],"performance.":[231]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}