{"id":"https://openalex.org/W4387074722","doi":"https://doi.org/10.48550/arxiv.2309.13077","title":"A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression","display_name":"A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression","publication_year":2023,"publication_date":"2023-09-21","ids":{"openalex":"https://openalex.org/W4387074722","doi":"https://doi.org/10.48550/arxiv.2309.13077"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.13077","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13077","pdf_url":"https://arxiv.org/pdf/2309.13077","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"},"parent_works":[],"lineage":["https://openalex.org/W4387074722"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.13077","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031130690","display_name":"Moonjung Eo","orcid":"https://orcid.org/0000-0002-0114-8010","observed_orcids":["https://orcid.org/0000-0002-0114-8010"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eo, Moonjung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017710330","display_name":"Suhyun Kang","orcid":"https://orcid.org/0000-0001-9772-1055","observed_orcids":["https://orcid.org/0000-0001-9772-1055"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kang, Suhyun","raw_affiliation_strings":["Deep Representation Learning Research Group , Department of Intelligence and Information , Seoul National University , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Representation Learning Research Group , Department of Intelligence and Information , Seoul National University , Seoul , South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056032525","display_name":"Wonjong Rhee","orcid":"https://orcid.org/0000-0002-2590-8774","observed_orcids":["https://orcid.org/0000-0002-2590-8774","https://orcid.org/0000-0002-9436-4627"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Rhee, Wonjong","raw_affiliation_strings":["Deep Representation Learning Research Group , Department of Intelligence and Information , Seoul National University , Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Representation Learning Research Group , Department of Intelligence and Information , Seoul National University , Seoul , South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9990000128746033,"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":0.9990000128746033,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00019999999494757503,"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":9.999999747378752e-05,"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/filter-pruning","display_name":"filter pruning","score":0.7609999775886536},{"id":"https://openalex.org/keywords/low-rank-decomposition","display_name":"low-rank decomposition","score":0.9850000143051147},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.8610000014305115},{"id":"https://openalex.org/keywords/singular-value-thresholding","display_name":"singular value thresholding","score":0.9300000071525574},{"id":"https://openalex.org/keywords/rank-based-selection","display_name":"rank selection","score":0.8460000157356262},{"id":"https://openalex.org/keywords/filter-selection","display_name":"filter selection","score":0.6399999856948853},{"id":"https://openalex.org/keywords/budget-constraints","display_name":"budget constraints","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694190502166748},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5116496682167053},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.48958858847618103},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.483360230922699},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48168954253196716},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.46734151244163513},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4542837142944336},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4515988230705261},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33012524247169495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3247874975204468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22801190614700317},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.13077","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13077","pdf_url":"https://arxiv.org/pdf/2309.13077","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.2309.13077","doi":"https://doi.org/10.48550/arxiv.2309.13077","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.13077","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.13077","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13077","pdf_url":"https://arxiv.org/pdf/2309.13077","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387074722.pdf","grobid_xml":"https://content.openalex.org/works/W4387074722.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2177847924","https://openalex.org/W2181101938","https://openalex.org/W2515385951","https://openalex.org/W2518108298","https://openalex.org/W2617247391","https://openalex.org/W2808168148","https://openalex.org/W2896006880","https://openalex.org/W2896409484","https://openalex.org/W2950967261","https://openalex.org/W2963094099","https://openalex.org/W2984574886","https://openalex.org/W3087585563","https://openalex.org/W3182242813","https://openalex.org/W4285601858"],"related_works":["https://openalex.org/W4396744168","https://openalex.org/W7155094558","https://openalex.org/W4387450399","https://openalex.org/W4283805579","https://openalex.org/W4387076356","https://openalex.org/W4317821327","https://openalex.org/W2980907007","https://openalex.org/W7213600955","https://openalex.org/W6910861383","https://openalex.org/W4413755593"],"abstract_inverted_index":{"Filter":[0],"pruning":[1],"and":[2,52,93,125],"low-rank":[3],"decomposition":[4],"are":[5],"two":[6],"of":[7,26,113],"the":[8,24,61,111],"foundational":[9],"techniques":[10],"for":[11,66,80,128],"structured":[12,98,117,130],"compression.":[13],"Although":[14],"recent":[15],"efforts":[16],"have":[17,32],"explored":[18],"hybrid":[19,97],"approaches":[20],"aiming":[21],"to":[22],"integrate":[23],"advantages":[25],"both":[27],"techniques,":[28],"their":[29],"performance":[30],"gains":[31],"been":[33],"modest":[34],"at":[35],"best.":[36],"In":[37],"this":[38],"study,":[39],"we":[40,63,77],"develop":[41],"a":[42,56,84,96,123],"\\textit{Differentiable":[43],"Framework~(DF)}":[44],"that":[45,101],"can":[46],"express":[47],"filter":[48,67],"selection,":[49,51,68,82],"rank":[50,81],"budget":[53],"constraint":[54],"into":[55,71],"single":[57],"analytical":[58],"formulation.":[59],"Within":[60],"framework,":[62],"introduce":[64],"DML-S":[65,92],"integrating":[69],"scheduling":[70],"existing":[72],"mask":[73],"learning":[74,104],"techniques.":[75,132],"Additionally,":[76],"present":[78],"DTL-S":[79,94],"utilizing":[83],"singular":[85],"value":[86],"thresholding":[87],"operator.":[88],"The":[89],"framework":[90],"with":[91],"offers":[95],"compression":[99,118,131],"methodology":[100],"facilitates":[102],"end-to-end":[103],"through":[105],"gradient-base":[106],"optimization.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"efficacy":[112],"DF,":[114],"surpassing":[115],"state-of-the-art":[116],"methods.":[119],"Our":[120],"work":[121],"establishes":[122],"robust":[124],"versatile":[126],"avenue":[127],"advancing":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2023-09-27T00:00:00"}