{"id":"https://openalex.org/W2777072123","doi":"https://doi.org/10.1109/dicta.2017.8227420","title":"Constrained Stochastic Gradient Descent: The Good Practice","display_name":"Constrained Stochastic Gradient Descent: The Good Practice","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2777072123","doi":"https://doi.org/10.1109/dicta.2017.8227420","mag":"2777072123"},"language":"en","primary_location":{"id":"doi:10.1109/dicta.2017.8227420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2017.8227420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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/A5104365769","display_name":"Soumava Kumar Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Soumava Kumar Roy","raw_affiliation_strings":["College of Engineering and Computer Science, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021790939","display_name":"Mehrtash Harandi","orcid":"https://orcid.org/0000-0002-6937-6300"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mehrtash Harandi","raw_affiliation_strings":["DATA61, CSIRO, ACT, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"DATA61, CSIRO, ACT, Canberra, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104365769"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.39,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.72106129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8838037848472595},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.7123818397521973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6815781593322754},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6555873155593872},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5675480961799622},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5547425746917725},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5508574843406677},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5454554557800293},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5223509073257446},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5208033323287964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165935754776001},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4843962788581848},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4204220473766327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40249350666999817},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35461288690567017},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23398831486701965},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12668085098266602}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8838037848472595},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7123818397521973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815781593322754},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6555873155593872},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5675480961799622},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5547425746917725},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5508574843406677},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5454554557800293},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5223509073257446},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5208033323287964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165935754776001},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4843962788581848},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4204220473766327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40249350666999817},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35461288690567017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23398831486701965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12668085098266602},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta.2017.8227420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2017.8227420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W1501362825","https://openalex.org/W1522301498","https://openalex.org/W1601795611","https://openalex.org/W1797268635","https://openalex.org/W1804110266","https://openalex.org/W1898424075","https://openalex.org/W1963882359","https://openalex.org/W1980287119","https://openalex.org/W1983496390","https://openalex.org/W1994616650","https://openalex.org/W2026892575","https://openalex.org/W2042182457","https://openalex.org/W2067752346","https://openalex.org/W2086161653","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2107438106","https://openalex.org/W2113097878","https://openalex.org/W2117198760","https://openalex.org/W2127589108","https://openalex.org/W2130062883","https://openalex.org/W2133323250","https://openalex.org/W2134603645","https://openalex.org/W2138674039","https://openalex.org/W2177410802","https://openalex.org/W2187483593","https://openalex.org/W2549348365","https://openalex.org/W2555897561","https://openalex.org/W2594807935","https://openalex.org/W2596142952","https://openalex.org/W2612083123","https://openalex.org/W2652783164","https://openalex.org/W2952372843","https://openalex.org/W2962798535","https://openalex.org/W2963026686","https://openalex.org/W2963173190","https://openalex.org/W2964121744","https://openalex.org/W3099206234","https://openalex.org/W3102317997","https://openalex.org/W4205293427","https://openalex.org/W4297817021","https://openalex.org/W4300092207","https://openalex.org/W6606156212","https://openalex.org/W6630053611","https://openalex.org/W6676105031","https://openalex.org/W6679314259","https://openalex.org/W6680086368","https://openalex.org/W6686785280","https://openalex.org/W6729295261","https://openalex.org/W6730323794","https://openalex.org/W6739448875"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W4391160746","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241"],"abstract_inverted_index":{"Stochastic":[0],"Gradient":[1],"Descent":[2],"(SGD)":[3],"is":[4],"the":[5,26,34],"method":[6],"of":[7,25,74,99],"choice":[8],"for":[9],"large":[10],"scale":[11],"problems,":[12],"most":[13],"notably":[14],"in":[15,55,95],"deep":[16,108],"learning.":[17,110],"Recent":[18],"studies":[19],"target":[20],"improving":[21],"convergence":[22],"and":[23,37,59,77,84,90,107],"speed":[24],"SGD":[27,35,65,86],"algorithm.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"equip":[33],"algorithm":[36],"its":[38],"advanced":[39],"versions":[40],"with":[41],"an":[42],"intriguing":[43],"feature,":[44],"namely":[45],"handling":[46],"constrained":[47,64],"problems.":[48],"Constraints":[49],"such":[50],"as":[51],"orthogonality":[52],"are":[53,67],"pervasive":[54],"learning":[56],"theory.":[57],"Nevertheless":[58],"to":[60,81],"some":[61],"extent":[62],"surprising,":[63],"algorithms":[66],"rarely":[68],"studied.":[69],"Our":[70],"proposal":[71],"makes":[72],"use":[73],"Riemannian":[75],"geometry":[76],"accelerated":[78],"optimization":[79],"techniques":[80],"deliver":[82],"efficient":[83],"constrained-aware":[85],"methods.We":[87],"will":[88],"assess":[89],"contrast":[91],"our":[92],"proposed":[93],"approaches":[94],"a":[96],"wide":[97],"range":[98],"problems":[100],"including":[101],"incremental":[102],"dimensionality":[103],"reduction,":[104],"karcher":[105],"mean":[106],"metric":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}