{"id":"https://openalex.org/W7134940655","doi":"https://doi.org/10.1109/icdmw69685.2025.00063","title":"JORTs: Jenk's Optimization for Restrictive Training","display_name":"JORTs: Jenk's Optimization for Restrictive Training","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134940655","doi":"https://doi.org/10.1109/icdmw69685.2025.00063"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105120705","display_name":"Jay Vap","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Vap","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128697160","display_name":"Reem Shehayib","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reem Shehayib","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029212199","display_name":"Peter M. Kogge","orcid":"https://orcid.org/0000-0002-3329-547X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Kogge","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73412094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"510","last_page":"519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.030700000002980232,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.030700000002980232,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10813","display_name":"Sport Psychology and Performance","score":0.024000000208616257,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11994","display_name":"Human Resource Development and Performance Evaluation","score":0.020899999886751175,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.42309999465942383},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.31459999084472656},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2524999976158142},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.24560000002384186},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.23739999532699585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5135999917984009},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.24560000002384186},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.23739999532699585},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23090000450611115},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.22529999911785126},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22380000352859497}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47159624099731445,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2097533491","https://openalex.org/W2112796928","https://openalex.org/W2135046866","https://openalex.org/W2156150815","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2808168148","https://openalex.org/W2963446712","https://openalex.org/W2977655572","https://openalex.org/W3065974826","https://openalex.org/W3121369352","https://openalex.org/W3198393051","https://openalex.org/W4214871172","https://openalex.org/W4255455317","https://openalex.org/W4327571587","https://openalex.org/W4400270653","https://openalex.org/W4401726555"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"networks":[1],"(NNs)":[2],"typically":[3],"demand":[4],"large":[5],"volumes":[6],"of":[7,26,81],"data":[8],"and":[9,21,43,92,96,98,110,135],"substantial":[10],"storage":[11],"capacity,":[12],"especially":[13],"when":[14],"overparameterized,":[15],"which":[16,56],"often":[17],"leads":[18],"to":[19,30,71],"redundancy":[20],"degraded":[22],"performance.":[23],"The":[24],"aim":[25],"this":[27,86,151],"work":[28],"is":[29,153],"address":[31],"redundant":[32],"and/or":[33],"unimportant":[34],"weights":[35],"through":[36],"model":[37],"compression":[38],"techniques,":[39],"focusing":[40],"on":[41,94,100,142],"pruning":[42,54,74],"quantization.":[44],"We":[45,84],"first":[46],"introduce":[47],"our":[48],"current":[49],"work,":[50],"a":[51],"novel":[52],"layer-wise":[53],"method,":[55],"combines":[57],"Global":[58],"Sparse":[59],"Momentum":[60],"SGD":[61],"(GSM-SGD)":[62],"first-order":[63],"saliency":[64],"scoring":[65],"with":[66,144],"Jenks'":[67],"Natural":[68],"Breaks":[69],"classification":[70],"dynamically":[72],"determine":[73],"thresholds":[75],"per":[76],"layer,":[77],"mitigating":[78],"the":[79],"risk":[80],"layer":[82],"collapse.":[83],"evaluate":[85],"approach":[87],"across":[88],"four":[89],"well-established":[90],"architectures-LeNet-5":[91],"LeNet-300-100":[93,121],"MNIST,":[95],"ResNet-56":[97,136],"DenseNet-40":[99,134],"CIFAR-10-while":[101],"tuning":[102],"hyperparameters":[103],"such":[104],"as":[105],"learning":[106],"rate,":[107],"weight":[108],"decay,":[109],"momentum.":[111],"Our":[112],"method":[113,152],"preserves":[114],"near-original":[115],"accuracy":[116,125],"post-pruning:":[117],"LeNet-5":[118],"maintains":[119],"98.75%,":[120],"retains":[122],"over":[123],"97%":[124,129],"while":[126],"achieving":[127],"around":[128],"sparsity":[130,147],"in":[131],"some":[132],"layers.":[133],"similarly":[137],"maintain":[138],"top-1":[139],"accuracies":[140],"(93.1%":[141],"CIFAR-10)":[143],"high":[145],"final":[146],"ratios.":[148],"Code":[149],"for":[150],"available":[154],"at":[155],"https://github.com/jvap2/If_I_could_turn_back_time/tree/master-jay":[156]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-12T00:00:00"}