{"id":"https://openalex.org/W7162393826","doi":"https://doi.org/10.48550/arxiv.2605.25499","title":"Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators","display_name":"Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162393826","doi":"https://doi.org/10.48550/arxiv.2605.25499"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25499","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25499","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.25499","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052139219","display_name":"Tongtong Fang","orcid":"https://orcid.org/0000-0001-9957-2292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Tongtong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137036588","display_name":"Nan Lu","orcid":"https://orcid.org/0000-0002-2631-6770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137056462","display_name":"Gang Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Gang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012922872","display_name":"Kenji Fukumizu","orcid":"https://orcid.org/0000-0002-3488-2625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fukumizu, Kenji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137056146","display_name":"Masashi Sugiyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sugiyama, Masashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12870000302791595,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12870000302791595,"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":0.08869999647140503,"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/T11448","display_name":"Face recognition and analysis","score":0.07129999995231628,"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/estimator","display_name":"Estimator","score":0.6912999749183655},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6852999925613403},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5735999941825867},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5722000002861023},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5618000030517578},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5598999857902527},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5292999744415283},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5271999835968018},{"id":"https://openalex.org/keywords/kernel-density-estimation","display_name":"Kernel density estimation","score":0.4715999960899353}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6852999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6050999760627747},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5735999941825867},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.4715999960899353},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26179999113082886},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25499","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25499","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.25499","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25499","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Importance":[0],"weighting":[1],"(IW)":[2],"is":[3],"a":[4,83,125,140,161,171],"golden":[5],"solver":[6],"for":[7,55,101,131,190],"joint":[8,13,135],"distribution":[9,136],"shift,":[10],"where":[11],"the":[12,17,36,105,178],"distributions":[14],"differ":[15],"between":[16],"training":[18,37],"and":[19,34,58,127,183,195],"test":[20],"data.":[21],"To":[22],"solve":[23],"this":[24,118],"problem,":[25],"IW":[26,44,54,106,129,203],"estimates":[27],"test-to-training":[28],"density":[29],"ratios":[30],"as":[31],"importance":[32],"weights":[33],"reweights":[35],"losses":[38],"accordingly.":[39],"Recent":[40],"advances":[41],"in":[42,72,92,170],"dynamic":[43],"(DIW)":[45],"integrate":[46],"weight":[47,102],"estimation":[48,110],"into":[49,160],"model":[50],"training,":[51],"enabling":[52],"scalable":[53],"deep":[56,132],"models":[57],"achieving":[59],"strong":[60],"performance":[61,204],"on":[62,99,113,177],"large":[63],"modern":[64],"datasets.":[65],"Despite":[66],"its":[67],"promise,":[68],"DIW":[69,123,159],"remains":[70],"limited":[71],"two":[73],"aspects.":[74],"First,":[75],"it":[76,96],"incurs":[77],"substantial":[78],"computational":[79],"overhead":[80],"by":[81],"solving":[82],"kernel":[84],"mean":[85],"matching":[86],"(KMM)-induced":[87],"optimization":[88],"problem":[89],"to":[90],"convergence":[91,188],"every":[93],"mini-batch.":[94],"Second,":[95],"relies":[97],"solely":[98],"KMM":[100],"estimation,":[103],"whereas":[104],"literature":[107],"contains":[108],"diverse":[109,167],"methods":[111,169],"based":[112,176],"different":[114],"divergence":[115],"measures.":[116],"In":[117],"paper,":[119],"we":[120],"propose":[121],"accelerated":[122],"(ADIW),":[124],"unified":[126,162],"efficient":[128],"framework":[130,164],"learning":[133],"under":[134,192],"shift.":[137],"ADIW":[138,157,191,200],"performs":[139],"few":[141],"lightweight":[142],"projected":[143],"gradient":[144],"descent":[145],"updates":[146],"that":[147,165,199],"warm-start":[148],"from":[149],"previously":[150],"updated":[151],"weights,":[152],"substantially":[153,207],"improving":[154],"efficiency.":[155],"Moreover,":[156],"generalizes":[158],"divergence-minimization":[163],"supports":[166],"weight-estimation":[168],"plug-and-play":[172],"manner,":[173],"including":[174],"those":[175],"Kullback-Leibler":[179],"divergence,":[180],"squared":[181],"distance,":[182],"Wasserstein-1":[184],"distance.":[185],"We":[186],"establish":[187],"guarantees":[189],"mild":[193],"conditions,":[194],"empirical":[196],"results":[197],"demonstrate":[198],"achieves":[201],"state-of-the-art":[202],"while":[205],"being":[206],"more":[208],"efficient.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-27T00:00:00"}