{"id":"https://openalex.org/W4386043276","doi":"https://doi.org/10.48550/arxiv.2308.09104","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":2023,"publication_date":"2023-08-17","ids":{"openalex":"https://openalex.org/W4386043276","doi":"https://doi.org/10.48550/arxiv.2308.09104"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2308.09104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.09104","pdf_url":"https://arxiv.org/pdf/2308.09104","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.09104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064019866","display_name":"Sanket Jantre","orcid":"https://orcid.org/0000-0003-3611-0255"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jantre, Sanket","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001978315","display_name":"Shrijita Bhattacharya","orcid":"https://orcid.org/0000-0001-6958-8613"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhattacharya, Shrijita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088272955","display_name":"Tapabrata Maiti","orcid":"https://orcid.org/0000-0002-9362-4984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maiti, Tapabrata","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":true,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9955000281333923,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9955000281333923,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9858999848365784,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9757000207901001,"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/prior-probability","display_name":"Prior probability","score":0.7370700240135193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.654271125793457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5783721208572388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.571081817150116},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.512859582901001},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5051193833351135},{"id":"https://openalex.org/keywords/lasso","display_name":"Lasso (programming language)","score":0.4711818993091583},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.361288845539093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3488870859146118},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33688902854919434}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7370700240135193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.654271125793457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5783721208572388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.571081817150116},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.512859582901001},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5051193833351135},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.4711818993091583},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.361288845539093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3488870859146118},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33688902854919434},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2308.09104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.09104","pdf_url":"https://arxiv.org/pdf/2308.09104","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2308.09104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.09104","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":"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":"pmh:oai:arXiv.org:2308.09104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.09104","pdf_url":"https://arxiv.org/pdf/2308.09104","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386043276.pdf"},"referenced_works_count":0,"referenced_works":[],"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/W4387595596","https://openalex.org/W2160108762","https://openalex.org/W1718066205","https://openalex.org/W2017034551","https://openalex.org/W2793406240"],"abstract_inverted_index":{"Network":[0],"complexity":[1],"and":[2,54,68,98,105,140,165],"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":[25,119,123,134,143,149,157],"underlying":[26],"target":[27],"function":[28,132],"reducing":[30],"heavily":[31],"over-parameterized":[32],"neural":[34,38,75,85],"networks.":[35,76],"Specifically,":[36],"architectures":[39],"compressed":[40],"via":[41],"structured":[42],"sparsity":[43],"(e.g.":[44],"node":[45,138],"sparsity)":[46],"provide":[47],"low":[48],"latency":[49],"inference,":[50],"higher":[51],"data":[52],"throughput,":[53],"reduced":[55],"energy":[56],"consumption.":[57],"In":[58],"this":[59,78],"paper,":[60],"we":[61,80],"explore":[62],"two":[63],"well-established":[64],"shrinkage":[65],"techniques,":[66],"Lasso":[67,96],"Horseshoe,":[69],"for":[70],"model":[71,163],"compression":[72],"in":[73,160],"Bayesian":[74,84],"To":[77],"end,":[79],"propose":[81],"structurally":[82],"networks":[86],"which":[87],"systematically":[88],"prune":[89],"excessive":[90],"nodes":[91],"with":[92],"(i)":[93],"Spike-and-Slab":[94,100],"Group":[95,101],"(SS-GL),":[97],"(ii)":[99],"Horseshoe":[102],"(SS-GHS)":[103],"priors,":[104],"develop":[106],"computationally":[107],"tractable":[108],"variational":[109,124],"inference":[110,166],"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],"layer-wise":[137],"cardinalities,":[139],"bounds":[141],"on":[142],"weights.":[145],"empirically":[147],"demonstrate":[148],"competitive":[150],"performance":[151],"compared":[155],"to":[156],"baseline":[158],"prediction":[161],"accuracy,":[162],"compression,":[164],"latency.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2023-08-22T00:00:00"}