{"id":"https://openalex.org/W4221151369","doi":"https://doi.org/10.48550/arxiv.2202.03770","title":"Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning","display_name":"Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning","publication_year":2022,"publication_date":"2022-02-08","ids":{"openalex":"https://openalex.org/W4221151369","doi":"https://doi.org/10.48550/arxiv.2202.03770"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2202.03770","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.03770","pdf_url":"https://arxiv.org/pdf/2202.03770","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.03770","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070743314","display_name":"Meet P. Vadera","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vadera, Meet P.","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030699148","display_name":"Adam D. Cobb","orcid":"https://orcid.org/0000-0003-2868-6983","observed_orcids":["https://orcid.org/0000-0003-2868-6983","https://orcid.org/0000-0002-6638-1788"]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cobb, Adam D.","raw_affiliation_strings":["SRI International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084773390","display_name":"Brian A. Jalaian","orcid":"https://orcid.org/0000-0003-3029-601X","observed_orcids":["https://orcid.org/0000-0003-3029-601X"]},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I4210088792","display_name":"United States Army","ror":"https://ror.org/00afsp483","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jalaian, Brian","raw_affiliation_strings":["US Army Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Army Research Laboratory","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I4210088792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023142437","display_name":"Benjamin M. Marlin","orcid":"https://orcid.org/0000-0002-2626-3410","observed_orcids":["https://orcid.org/0000-0002-2626-3410"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marlin, Benjamin M.","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.8202999830245972,"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"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.8202999830245972,"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":0.1388999968767166,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.012199999764561653,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/bayesian-deep-learning","display_name":"Bayesian deep learning","score":0.8450000286102295},{"id":"https://openalex.org/keywords/stochastic-gradient-mcmc","display_name":"stochastic gradient MCMC","score":0.9700000286102295},{"id":"https://openalex.org/keywords/parameter-sparsity","display_name":"parameter sparsity","score":0.8190000057220459},{"id":"https://openalex.org/keywords/sparse-network-structure","display_name":"sparse network structure","score":0.7289999723434448},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"uncertainty quantification","score":0.9229999780654907},{"id":"https://openalex.org/keywords/inference-runtime","display_name":"inference runtime","score":0.6909999847412109},{"id":"https://openalex.org/keywords/network-pruning","display_name":"network pruning","score":0.5410000085830688},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.8119999766349792},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.6819999814033508}],"concepts":[{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.864440381526947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6755382418632507},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6170424222946167},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.615669310092926},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5946556329727173},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5830123424530029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5757715702056885},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.535094141960144},{"id":"https://openalex.org/C71983512","wikidata":"https://www.wikidata.org/wiki/Q7915687","display_name":"Variable-order Bayesian network","level":4,"score":0.49744608998298645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4921380877494812},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4458678662776947},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2202.03770","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.03770","pdf_url":"https://arxiv.org/pdf/2202.03770","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2202.03770","doi":"https://doi.org/10.48550/arxiv.2202.03770","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2202.03770","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.03770","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.03770","pdf_url":"https://arxiv.org/pdf/2202.03770","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1198325749","display_name":null,"funder_award_id":"W911NF-17-2-0196.","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4307315608","https://openalex.org/W4399849626","https://openalex.org/W2990377910","https://openalex.org/W4394664561","https://openalex.org/W3039635988","https://openalex.org/W6889142880","https://openalex.org/W3193572680","https://openalex.org/W4403936882","https://openalex.org/W4378473987","https://openalex.org/W3103031059"],"abstract_inverted_index":{"Bayesian":[0,29,41,111],"methods":[1,31,54,107,147],"hold":[2],"significant":[3],"promise":[4],"for":[5,32,120],"improving":[6],"the":[7,22,39,57,64,79,109],"uncertainty":[8,99],"quantification":[9,100],"ability":[10],"and":[11,42,70,91,98,114],"robustness":[12],"of":[13,24,27,66,81,118,132],"deep":[14,33],"neural":[15,34],"network":[16,83,123],"models.":[17],"Recent":[18],"research":[19],"has":[20],"seen":[21],"investigation":[23],"a":[25,116],"number":[26],"approximate":[28],"inference":[30,92,112],"networks,":[35],"building":[36],"on":[37],"both":[38],"variational":[40],"Markov":[43],"chain":[44],"Monte":[45],"Carlo":[46],"(MCMC)":[47],"frameworks.":[48],"A":[49],"fundamental":[50],"issue":[51],"with":[52],"MCMC":[53,106],"is":[55],"that":[56,129],"improvements":[58],"they":[59],"enable":[60],"are":[61],"obtained":[62],"at":[63],"expense":[65],"increased":[67],"computation":[68],"time":[69,94],"model":[71,88,151],"storage":[72,89],"costs.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"investigate":[78],"potential":[80],"sparse":[82,122],"structures":[84],"to":[85],"flexibly":[86],"trade-off":[87],"costs":[90],"run":[93],"against":[95],"predictive":[96],"performance":[97],"ability.":[101],"We":[102],"use":[103],"stochastic":[104],"gradient":[105],"as":[108,138,140],"core":[110],"method":[113],"consider":[115],"variety":[117],"approaches":[119],"selecting":[121],"structures.":[124],"Surprisingly,":[125],"our":[126],"results":[127],"show":[128],"certain":[130],"classes":[131],"randomly":[133],"selected":[134],"substructures":[135,141],"can":[136],"perform":[137],"well":[139],"derived":[142],"from":[143],"state-of-the-art":[144],"iterative":[145],"pruning":[146],"while":[148],"drastically":[149],"reducing":[150],"training":[152],"times.":[153]},"counts_by_year":[],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2022-04-03T00:00:00"}