{"id":"https://openalex.org/W4403936882","doi":"https://doi.org/10.1109/tnnls.2024.3485529","title":"Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks","display_name":"Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4403936882","doi":"https://doi.org/10.1109/tnnls.2024.3485529","pmid":"https://pubmed.ncbi.nlm.nih.gov/39480710"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3485529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3485529","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064019866","display_name":"Sanket Jantre","orcid":"https://orcid.org/0000-0003-3611-0255"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanket Jantre","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001978315","display_name":"Shrijita Bhattacharya","orcid":"https://orcid.org/0000-0001-6958-8613"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrijita Bhattacharya","raw_affiliation_strings":["Department of Statistics and Probability, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Probability, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088272955","display_name":"Tapabrata Maiti","orcid":"https://orcid.org/0000-0002-9362-4984"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tapabrata Maiti","raw_affiliation_strings":["Department of Statistics and Probability, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Probability, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064019866"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":1.9311,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88101662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"36","issue":"6","first_page":"11176","last_page":"11188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9690999984741211,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9690999984741211,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9674000144004822,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9498999714851379,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spike","display_name":"Spike (software development)","score":0.9169484376907349},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.875471830368042},{"id":"https://openalex.org/keywords/shrinkage","display_name":"Shrinkage","score":0.8468868732452393},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6488654017448425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4882092773914337},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4602126181125641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4500192403793335},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.43700048327445984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41701942682266235},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30894735455513}],"concepts":[{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.9169484376907349},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.875471830368042},{"id":"https://openalex.org/C180145272","wikidata":"https://www.wikidata.org/wiki/Q7504144","display_name":"Shrinkage","level":2,"score":0.8468868732452393},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6488654017448425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4882092773914337},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4602126181125641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4500192403793335},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.43700048327445984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41701942682266235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30894735455513},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3485529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3485529","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39480710","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39480710","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2047229728","https://openalex.org/W2082633919","https://openalex.org/W2116006439","https://openalex.org/W2128925311","https://openalex.org/W2194775991","https://openalex.org/W2225156818","https://openalex.org/W2612481336","https://openalex.org/W2749772809","https://openalex.org/W2756210560","https://openalex.org/W2768228643","https://openalex.org/W2783538964","https://openalex.org/W2922301133","https://openalex.org/W2938262174","https://openalex.org/W2962834855","https://openalex.org/W2962851801","https://openalex.org/W2963545688","https://openalex.org/W2964233199","https://openalex.org/W2964266063","https://openalex.org/W2965710672","https://openalex.org/W2971678291","https://openalex.org/W2980069674","https://openalex.org/W2998508940","https://openalex.org/W3035587749","https://openalex.org/W3134482315","https://openalex.org/W3193572680","https://openalex.org/W4229774059","https://openalex.org/W4249083122","https://openalex.org/W4320930577","https://openalex.org/W6604254268","https://openalex.org/W6674330103","https://openalex.org/W6724998850","https://openalex.org/W6728514080","https://openalex.org/W6729448088","https://openalex.org/W6729614184","https://openalex.org/W6730091202","https://openalex.org/W6730382033","https://openalex.org/W6732814185","https://openalex.org/W6738806959","https://openalex.org/W6738951869","https://openalex.org/W6739000085","https://openalex.org/W6743688258","https://openalex.org/W6745148473","https://openalex.org/W6748728731","https://openalex.org/W6749530404","https://openalex.org/W6751979845","https://openalex.org/W6759263581","https://openalex.org/W6762947928","https://openalex.org/W6764214684","https://openalex.org/W6766978945","https://openalex.org/W6786174422"],"related_works":["https://openalex.org/W2562263695","https://openalex.org/W2135187896","https://openalex.org/W2147201983","https://openalex.org/W2015518264","https://openalex.org/W2795035211","https://openalex.org/W2160108762","https://openalex.org/W2017034551","https://openalex.org/W2164129707","https://openalex.org/W4292122269","https://openalex.org/W2949366006"],"abstract_inverted_index":{"Network":[0],"complexity":[1],"and":[2,53,67,98,105,140,165],"computational":[3],"efficiency":[4],"have":[5],"become":[6],"increasingly":[7],"significant":[8],"aspects":[9],"of":[10,24,114,122,126,133,152],"deep":[11,14,33,37],"learning.":[12],"Sparse":[13],"learning":[15],"addresses":[16],"these":[17],"challenges":[18],"by":[19,29],"recovering":[20],"a":[21,131],"sparse":[22,83],"representation":[23],"the":[25,91,119,123,134,143,149,157],"underlying":[26],"target":[27],"function":[28,132],"reducing":[30],"heavily":[31],"overparameterized":[32],"neural":[34,38,74],"networks.":[35],"Specifically,":[36],"architectures":[39],"compressed":[40],"via":[41],"structured":[42],"sparsity":[43],"(e.g.,":[44],"node":[45,138],"sparsity)":[46],"provide":[47],"low-latency":[48],"inference,":[49,110],"higher":[50],"data":[51],"throughput,":[52],"reduced":[54],"energy":[55],"consumption.":[56],"In":[57],"this":[58,78],"article,":[59],"we":[60,80],"explore":[61],"two":[62],"well-established":[63],"shrinkage":[64],"techniques,":[65],"Lasso":[66,96],"Horseshoe,":[68],"for":[69],"model":[70,163],"compression":[71],"in":[72,160],"Bayesian":[73],"networks":[75],"(BNNs).":[76],"To":[77],"end,":[79],"propose":[81],"structurally":[82],"BNNs,":[84],"which":[85],"systematically":[86],"prune":[87],"excessive":[88],"nodes":[89],"with":[90,156],"following:":[92],"1)":[93],"spike-and-slab":[94],"group":[95,101],"(SS-GL)":[97],"2)":[99],"SS":[100],"Horseshoe":[102],"(SS-GHS)":[103],"priors,":[104],"develop":[106],"computationally":[107],"tractable":[108],"variational":[109,124],"including":[111],"continuous":[112],"relaxation":[113],"Bernoulli":[115],"variables.":[116],"We":[117,146],"establish":[118],"contraction":[120],"rates":[121],"posterior":[125],"our":[127,153],"proposed":[128],"models":[129,154,159],"as":[130],"network":[135,144],"topology,":[136],"layerwise":[137],"cardinalities,":[139],"bounds":[141],"on":[142],"weights.":[145],"empirically":[147],"demonstrate":[148],"competitive":[150],"performance":[151],"compared":[155],"baseline":[158],"prediction":[161],"accuracy,":[162],"compression,":[164],"inference":[166],"latency.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}