{"id":"https://openalex.org/W7150881771","doi":"https://doi.org/10.48550/arxiv.2604.02513","title":"Sparse Bayesian Learning Algorithms Revisited: From Learning Majorizers to Structured Algorithmic Learning using Neural Networks","display_name":"Sparse Bayesian Learning Algorithms Revisited: From Learning Majorizers to Structured Algorithmic Learning using Neural Networks","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7150881771","doi":"https://doi.org/10.48550/arxiv.2604.02513"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.02513","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02513","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.02513","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089242792","display_name":"Rushabha Balaji","orcid":"https://orcid.org/0009-0002-7115-5432"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balaji, Rushabha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133055643","display_name":"Kuan-Lin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kuan-Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008128583","display_name":"Danijela \u010cabri\u0107","orcid":"https://orcid.org/0000-0002-5967-2683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cabric, Danijela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108088237","display_name":"Bhaskar D. Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Bhaskar D.","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":0.9067000150680542,"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":0.9067000150680542,"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":0.014000000432133675,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.012799999676644802,"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/convergence","display_name":"Convergence (economics)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4650000035762787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4553000032901764},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4496999979019165},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4422999918460846},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4388999938964844},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.39800000190734863},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.39169999957084656},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694599986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6808000206947327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6492000222206116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.620199978351593},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.39169999957084656},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C17061570","wikidata":"https://www.wikidata.org/wiki/Q7960888","display_name":"Wake-sleep algorithm","level":4,"score":0.35280001163482666},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2955999970436096},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.02513","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02513","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.02513","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02513","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6264184713363647}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"Bayesian":[1],"Learning":[2],"is":[3,32,44],"one":[4],"of":[5,51,88,139,168,176,277],"the":[6,18,37,67,76,95,106,137,145,152,159,164,174,199,216,243],"most":[7,68,97],"popular":[8,69,98],"sparse":[9,28,206],"signal":[10],"recovery":[11,29,207],"methods,":[12],"and":[13,26,130,142,241,281],"various":[14],"algorithms":[15,71],"exist":[16],"under":[17,105],"SBL":[19,57,70,89,99,140,147,177,184],"paradigm.":[20],"However,":[21],"given":[22],"a":[23,27,49,52,116,120,182,191,222,257],"performance":[24,263,273],"metric":[25],"problem,":[30],"it":[31],"difficult":[33],"to":[34,40,48,55,85,171,180,225,239,255],"know":[35],"a-priori":[36],"best":[38,146],"algorithm":[39,148],"choose.":[41],"This":[42],"difficulty":[43],"in":[45],"part":[46],"due":[47],"lack":[50],"unified":[53],"framework":[54,108,161],"derive":[56],"algorithms.":[58,126],"We":[59,189,249],"address":[60,143],"this":[61,86,128,235],"issue":[62],"by":[63,162,260],"first":[64],"showing":[65],"that":[66,94,196],"can":[72,197],"be":[73],"derived":[74],"using":[75],"majorization-minimization":[77],"(MM)":[78],"principle,":[79],"providing":[80,221],"hitherto":[81],"unknown":[82],"convergence":[83],"guarantees":[84],"class":[87,138,175],"methods.":[90],"Moreover,":[91],"we":[92,135,156,269],"show":[93],"two":[96],"update":[100,185],"rules":[101],"not":[102,213],"only":[103],"fall":[104],"MM":[107,133,153,160,201],"but":[109],"are":[110],"both":[111],"valid":[112],"descent":[113],"steps":[114],"for":[115],"common":[117],"majorizer,":[118],"revealing":[119],"deeper":[121],"analytical":[122],"compatibility":[123],"between":[124],"these":[125],"Using":[127],"insight":[129],"properties":[131],"from":[132,187],"theory":[134],"expand":[136,173],"algorithms,":[141,178],"finding":[144],"via":[149],"data":[150],"within":[151],"framework.":[154],"Second,":[155],"go":[157],"beyond":[158],"introducing":[163],"powerful":[165],"modeling":[166],"capabilities":[167],"deep":[169,193],"learning":[170,194],"further":[172],"aiming":[179],"learn":[181,256],"superior":[183],"rule":[186],"data.":[188],"propose":[190],"novel":[192],"architecture":[195],"outperform":[198],"classical":[200],"based":[202],"ones":[203],"across":[204,229,245,274],"different":[205,230,246,275],"problems.":[208],"Our":[209],"architecture's":[210],"complexity":[211],"does":[212],"scale":[214],"with":[215],"measurement":[217,266],"matrix":[218],"dimension,":[219],"hence":[220],"unique":[223],"opportunity":[224],"test":[226,242,270],"generalization":[227],"capability":[228],"matrices.":[231,267],"For":[232],"parameterized":[233],"dictionaries,":[234],"invariance":[236],"allows":[237],"us":[238],"train":[240],"model":[244],"parameter":[247],"ranges.":[248],"also":[250],"showcase":[251],"our":[252,271],"model's":[253,272],"ability":[254],"functional":[258],"mapping":[259],"its":[261],"zero-shot":[262],"on":[264],"unseen":[265],"Finally,":[268],"numbers":[276],"snapshots,":[278],"signal-to-noise":[279],"ratios,":[280],"sparsity":[282],"levels.":[283]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-07T00:00:00"}