{"id":"https://openalex.org/W4297412339","doi":"https://doi.org/10.48550/arxiv.2209.11785","title":"Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search","display_name":"Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search","publication_year":2022,"publication_date":"2022-09-23","ids":{"openalex":"https://openalex.org/W4297412339","doi":"https://doi.org/10.48550/arxiv.2209.11785"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.11785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11785","pdf_url":"https://arxiv.org/pdf/2209.11785","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":null,"license_id":null,"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/2209.11785","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026905950","display_name":"S\u0142awomir Kierat","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kierat, S\u0142awomir","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036764039","display_name":"Mateusz Sieniawski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sieniawski, Mateusz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069168410","display_name":"Denys Fridman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fridman, Denys","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334657","display_name":"Chenhan D. Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Chen-Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031316782","display_name":"Szymon Migacz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Migacz, Szymon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069742186","display_name":"Pawe\u0142 Morkisz","orcid":"https://orcid.org/0000-0002-4734-966X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morkisz, Pawe\u0142","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070337944","display_name":"Alex-Fit Florea","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florea, Alex-Fit","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5026905950"],"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":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7384469509124756},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7263489961624146},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7014185190200806},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5316892862319946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42643052339553833},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34710514545440674},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34045714139938354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3288753926753998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384469509124756},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7263489961624146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7014185190200806},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5316892862319946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42643052339553833},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34710514545440674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34045714139938354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3288753926753998},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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:2209.11785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11785","pdf_url":"https://arxiv.org/pdf/2209.11785","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.11785","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.11785","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.11785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11785","pdf_url":"https://arxiv.org/pdf/2209.11785","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"We":[0],"propose":[1],"three":[2],"novel":[3,65],"pruning":[4,49,68],"techniques":[5],"to":[6,125],"improve":[7],"the":[8,56,59,73,80,116],"cost":[9],"and":[10,40,85,113],"results":[11],"of":[12,55,97],"inference-aware":[13],"Differentiable":[14],"Neural":[15],"Architecture":[16],"Search":[17],"(DNAS).":[18],"First,":[19],"we":[20,44,62],"introduce":[21],"Prunode,":[22],"a":[23,52,64,87,108],"stochastic":[24,53,70],"bi-path":[25],"building":[26],"block":[27],"for":[28,48,67,92,100],"DNAS,":[29],"which":[30],"can":[31],"search":[32,81],"over":[33],"inner":[34],"hidden":[35],"dimensions":[36],"with":[37],"O(1)":[38],"memory":[39],"compute":[41],"complexity.":[42],"Second,":[43],"present":[45],"an":[46],"algorithm":[47],"blocks":[50],"within":[51],"layer":[54],"SuperNet":[57],"during":[58,72],"search.":[60,74],"Third,":[61],"describe":[63],"technique":[66],"unnecessary":[69],"layers":[71],"The":[75],"optimized":[76],"models":[77],"resulting":[78],"from":[79],"are":[82],"called":[83],"PruNet":[84,106],"establishes":[86],"new":[88],"state-of-the-art":[89],"Pareto":[90],"frontier":[91],"NVIDIA":[93],"V100":[94],"in":[95],"terms":[96],"inference":[98,122],"latency":[99,123],"ImageNet":[101],"Top-1":[102],"image":[103],"classification":[104],"accuracy.":[105],"as":[107],"backbone":[109],"also":[110],"outperforms":[111],"GPUNet":[112],"EfficientNet":[114],"on":[115,121],"COCO":[117],"object":[118],"detection":[119],"task":[120],"relative":[124],"mean":[126],"Average":[127],"Precision":[128],"(mAP).":[129]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2022-09-28T00:00:00"}