{"id":"https://openalex.org/W3039189175","doi":null,"title":"Understanding Diversity based Pruning of Neural Networks - Statistical Mechanical Analysis.","display_name":"Understanding Diversity based Pruning of Neural Networks - Statistical Mechanical Analysis.","publication_year":2020,"publication_date":"2020-06-30","ids":{"openalex":"https://openalex.org/W3039189175","mag":"3039189175"},"language":"en","primary_location":{"id":"mag:3039189175","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.16617","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.16617","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039599566","display_name":"Rupam Acharyya","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rupam Acharyya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714035","display_name":"Boyu Zhang","orcid":"https://orcid.org/0000-0001-8012-9311","observed_orcids":["https://orcid.org/0000-0001-8012-9311","https://orcid.org/0009-0007-7428-608X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyu Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8012-9311","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089676445","display_name":"Ankani Chattoraj","orcid":"https://orcid.org/0000-0002-7644-667X","observed_orcids":["https://orcid.org/0000-0002-7644-667X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankani Chattoraj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shouman Das","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shouman Das","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088287514","display_name":"Daniel \u0160tefankovi\u010d","orcid":"https://orcid.org/0000-0002-4849-7955","observed_orcids":["https://orcid.org/0000-0002-4849-7955"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel \u0160tefankovi\u010d","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4849-7955","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/T10036","display_name":"Advanced Neural Network Applications","score":0.8866999745368958,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8866999745368958,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.05979999899864197,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.02850000001490116,"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/neural-network-pruning","display_name":"neural network pruning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/statistical-mechanics","display_name":"statistical mechanics","score":0.6710000038146973},{"id":"https://openalex.org/keywords/teacher-student-models","display_name":"teacher-student models","score":0.9129999876022339},{"id":"https://openalex.org/keywords/generalization-bounds","display_name":"generalization bounds","score":0.9829999804496765},{"id":"https://openalex.org/keywords/determinantal-point-processes","display_name":"determinantal point processes","score":0.9259999990463257},{"id":"https://openalex.org/keywords/edge-pruning","display_name":"edge pruning","score":0.8889999985694885},{"id":"https://openalex.org/keywords/node-pruning","display_name":"node pruning","score":0.8960000276565552},{"id":"https://openalex.org/keywords/neural-network-compression","display_name":"neural network compression","score":0.7400000095367432},{"id":"https://openalex.org/keywords/sparse-neural-networks","display_name":"sparse neural networks","score":0.8510000109672546}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.885999321937561},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694710373878479},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6752356886863708},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5481408834457397},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5349211692810059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5284754037857056},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5120878219604492},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49915242195129395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49060145020484924},{"id":"https://openalex.org/C72010251","wikidata":"https://www.wikidata.org/wiki/Q5265688","display_name":"Determinantal point process","level":4,"score":0.4410552978515625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27315253019332886},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07589367032051086},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C64812099","wikidata":"https://www.wikidata.org/wiki/Q176604","display_name":"Random matrix","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3039189175","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.16617","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3039189175","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.16617","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1966695467","https://openalex.org/W1966776414","https://openalex.org/W1995842804","https://openalex.org/W2006672084","https://openalex.org/W2058641082","https://openalex.org/W2084910356","https://openalex.org/W2114766824","https://openalex.org/W2125389748","https://openalex.org/W2138779671","https://openalex.org/W2149298154","https://openalex.org/W2251939518","https://openalex.org/W2515385951","https://openalex.org/W2593729559","https://openalex.org/W2616340865","https://openalex.org/W2763894180","https://openalex.org/W2785885194","https://openalex.org/W2788851830","https://openalex.org/W2805003733","https://openalex.org/W2809090039","https://openalex.org/W2894740066","https://openalex.org/W2915589364","https://openalex.org/W2942052807","https://openalex.org/W2950404682","https://openalex.org/W2951598131","https://openalex.org/W2963145730","https://openalex.org/W2963341956","https://openalex.org/W2963363373","https://openalex.org/W2963993763","https://openalex.org/W2964299589","https://openalex.org/W2981407587","https://openalex.org/W2990461664","https://openalex.org/W3010156474","https://openalex.org/W3034877463","https://openalex.org/W3035615218","https://openalex.org/W3036957384","https://openalex.org/W3038185437","https://openalex.org/W3118608800","https://openalex.org/W3173173537"],"related_works":["https://openalex.org/W3167325898","https://openalex.org/W3035105259","https://openalex.org/W2888303193","https://openalex.org/W6891839126","https://openalex.org/W2616340865","https://openalex.org/W7163423429","https://openalex.org/W2979789219","https://openalex.org/W6929619974","https://openalex.org/W4415796392","https://openalex.org/W7111137427"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"architectures":[2],"with":[3],"a":[4,55,150,185],"huge":[5],"number":[6,152],"of":[7,19,25,33,36,54,64,83,153],"parameters":[8],"are":[9],"often":[10],"compressed":[11],"using":[12],"pruning":[13,38,66,74,88,101,166,173,188,198],"techniques":[14],"to":[15,80,106,160,183],"ensure":[16],"computational":[17],"efficiency":[18],"inference":[20],"during":[21],"deployment.":[22],"Despite":[23],"multitude":[24],"empirical":[26,127],"advances,":[27],"there":[28],"is":[29,103,134],"no":[30],"theoretical":[31,69,123,158,181],"understanding":[32],"the":[34,47,50,118],"effectiveness":[35],"different":[37],"methods.":[39,67,89],"We":[40,155],"address":[41],"this":[42],"issue":[43],"by":[44],"setting":[45],"up":[46],"problem":[48],"in":[49,117,132],"statistical":[51],"mechanics":[52],"formulation":[53],"teacher-student":[56],"framework":[57],"and":[58,76],"deriving":[59],"generalization":[60],"error":[61],"(GE)":[62],"bounds":[63,116],"specific":[65],"This":[68],"premise":[70],"allows":[71],"comparison":[72],"between":[73],"methods":[75,199],"we":[77,121,176],"use":[78,156],"it":[79],"investigate":[81],"compression":[82],"neural":[84,137,145,191],"networks":[85,138,146,192],"via":[86],"diversity-based":[87],"A":[90],"recent":[91],"work":[92],"showed":[93],"that":[94,135,162],"Determinantal":[95],"Point":[96],"Process":[97],"(DPP)":[98],"based":[99],"node":[100,172],"method":[102,167],"notably":[104],"superior":[105],"competing":[107,197],"approaches":[108],"when":[109],"tested":[110],"on":[111,200],"real":[112,201],"datasets.":[113,202],"Using":[114],"GE":[115],"aforementioned":[119],"setup":[120,159],"provide":[122],"guarantees":[124],"for":[125,149,190],"their":[126],"observations.":[128],"Another":[129],"consistent":[130],"finding":[131],"literature":[133],"sparse":[136],"(edge":[139],"pruned)":[140,148],"generalize":[141],"better":[142,169],"than":[143,170],"dense":[144],"(node":[147],"fixed":[151],"parameters.":[154],"our":[157,180],"prove":[161],"baseline":[163],"random":[164],"edge":[165,187],"performs":[168],"DPP":[171,186],"method.":[174],"Finally,":[175],"draw":[177],"motivation":[178],"from":[179],"results":[182],"propose":[184],"technique":[189],"which":[193],"empirically":[194],"outperforms":[195],"other":[196]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-07-10T00:00:00"}