{"id":"https://openalex.org/W2964928445","doi":"https://doi.org/10.24963/ijcai.2019/372","title":"Submodular Batch Selection for Training Deep Neural Networks","display_name":"Submodular Batch Selection for Training Deep Neural Networks","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964928445","doi":"https://doi.org/10.24963/ijcai.2019/372","mag":"2964928445"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/372","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/372","pdf_url":"https://www.ijcai.org/proceedings/2019/0372.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0372.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035656808","display_name":"K J Joseph","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K J Joseph","raw_affiliation_strings":["Indian Institute of Technology, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024380274","display_name":"Vamshi Teja R","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vamshi Teja R","raw_affiliation_strings":["Indian Institute of Technology, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060320135","display_name":"Krishnakant Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishnakant Singh","raw_affiliation_strings":["Indian Institute of Technology, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038020125","display_name":"Vineeth N Balasubramanian","orcid":"https://orcid.org/0000-0003-2656-0375"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vineeth N Balasubramanian","raw_affiliation_strings":["Indian Institute of Technology, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5038020125"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2677","last_page":"2683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9997000098228455,"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":0.9994999766349792,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9988999962806702,"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/submodular-set-function","display_name":"Submodular set function","score":0.9347755908966064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7180569767951965},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7117565870285034},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.629520833492279},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.568626344203949},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5195915699005127},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5070738792419434},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49703338742256165},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.482822984457016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47393709421157837},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.44656872749328613},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.44628968834877014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4216899871826172},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28799617290496826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22056254744529724}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.9347755908966064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180569767951965},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7117565870285034},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.629520833492279},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.568626344203949},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5195915699005127},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5070738792419434},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49703338742256165},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.482822984457016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47393709421157837},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.44656872749328613},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.44628968834877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4216899871826172},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28799617290496826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22056254744529724},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/372","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/372","pdf_url":"https://www.ijcai.org/proceedings/2019/0372.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/372","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/372","pdf_url":"https://www.ijcai.org/proceedings/2019/0372.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964928445.pdf","grobid_xml":"https://content.openalex.org/works/W2964928445.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1680189815","https://openalex.org/W1836465849","https://openalex.org/W1842094663","https://openalex.org/W1898824936","https://openalex.org/W1912128066","https://openalex.org/W1984985727","https://openalex.org/W2025566624","https://openalex.org/W2072566913","https://openalex.org/W2107438106","https://openalex.org/W2113097878","https://openalex.org/W2144933361","https://openalex.org/W2170735271","https://openalex.org/W2194775991","https://openalex.org/W2307132432","https://openalex.org/W2335728318","https://openalex.org/W2609701267","https://openalex.org/W2621265919","https://openalex.org/W2884664079","https://openalex.org/W2899771611","https://openalex.org/W2917620156","https://openalex.org/W2962685744","https://openalex.org/W2963607709","https://openalex.org/W2963941666","https://openalex.org/W2964220187","https://openalex.org/W3118608800","https://openalex.org/W4294583774","https://openalex.org/W4294635920","https://openalex.org/W4300092207"],"related_works":["https://openalex.org/W2402949237","https://openalex.org/W2594118609","https://openalex.org/W2765425000","https://openalex.org/W3204684126","https://openalex.org/W2735578456","https://openalex.org/W4389478405","https://openalex.org/W2944632132","https://openalex.org/W2901206941","https://openalex.org/W2968699064","https://openalex.org/W2354484762"],"abstract_inverted_index":{"Mini-batch":[0],"gradient":[1],"descent":[2],"based":[3,21],"methods":[4],"are":[5],"the":[6,31,39,67,72],"de":[7],"facto":[8],"algorithms":[9],"for":[10],"training":[11],"neural":[12],"network":[13],"architectures":[14],"today.We":[15],"introduce":[16],"a":[17,87],"mini-batch":[18],"selection":[19,75],"strategy":[20,76,91],"on":[22,62],"submodular":[23,28],"function":[24],"maximization.":[25],"Our":[26,59],"novel":[27],"formulation":[29],"captures":[30],"informativeness":[32],"of":[33,38],"each":[34],"sample":[35],"and":[36,98],"diversity":[37],"whole":[40],"subset.":[41],"We":[42],"design":[43],"an":[44],"efficient,":[45],"greedy":[46],"algorithm":[47],"which":[48],"can":[49],"give":[50],"high-quality":[51],"solutions":[52],"to":[53],"this":[54],"NP-hard":[55],"combinatorial":[56],"optimization":[57],"problem.":[58],"extensive":[60],"experiments":[61],"standard":[63],"datasets":[64],"show":[65],"that":[66],"deep":[68],"models":[69],"trained":[70],"using":[71],"proposed":[73],"batch":[74,96],"provide":[77],"better":[78],"generalization":[79],"than":[80],"Stochastic":[81],"Gradient":[82],"Descent":[83],"as":[84,86],"well":[85],"popular":[88],"baseline":[89],"sampling":[90],"across":[92],"different":[93],"learning":[94],"rates,":[95],"sizes,":[97],"distance":[99],"metrics.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}