{"id":"https://openalex.org/W7135195690","doi":"https://doi.org/10.1109/tpami.2026.3674120","title":"Nonlinear Bayesian Filtering With <b>N</b> atural Gr <b>a</b> dient Gaussia <b>n</b> Appr <b>o</b> ximation","display_name":"Nonlinear Bayesian Filtering With <b>N</b> atural Gr <b>a</b> dient Gaussia <b>n</b> Appr <b>o</b> ximation","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7135195690","doi":"https://doi.org/10.1109/tpami.2026.3674120","pmid":"https://pubmed.ncbi.nlm.nih.gov/41824332"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3674120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3674120","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102751432","display_name":"Wenhan Cao","orcid":"https://orcid.org/0009-0001-1367-4210"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Cao","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1367-4210","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437440","display_name":"Tianyi Zhang","orcid":"https://orcid.org/0009-0003-1335-9784"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-2742-3525","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008394333","display_name":"Zeju Sun","orcid":"https://orcid.org/0009-0008-9348-1988"},"institutions":[{"id":"https://openalex.org/I4403928416","display_name":"Beijing Institute of Mathematical Sciences and Applications","ror":"https://ror.org/05t6hvr95","country_code":null,"type":"education","lineage":["https://openalex.org/I4403928416","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeju Sun","raw_affiliation_strings":["Beijing Institute of Mathematical Sciences and Applications (BIMSA), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9348-1988","affiliations":[{"raw_affiliation_string":"Beijing Institute of Mathematical Sciences and Applications (BIMSA), Beijing, China","institution_ids":["https://openalex.org/I4403928416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128945773","display_name":"Chang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["School of Advanced Manufacturing and Robotics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7686-2510","affiliations":[{"raw_affiliation_string":"School of Advanced Manufacturing and Robotics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108541576","display_name":"Stephen S.-T. Yau","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Stephen S.-T. Yau","raw_affiliation_strings":["Department of Mathematical Sciences, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7634-7981","affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040156274","display_name":"Changliu Liu","orcid":"https://orcid.org/0000-0002-3767-5517"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility and College of Artificial Intelligence, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4923-3633","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility and College of Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.25523758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"48","issue":"7","first_page":"8581","last_page":"8597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.20000000298023224,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.20000000298023224,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.17800000309944153,"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/T12261","display_name":"Statistical Mechanics and Entropy","score":0.06589999794960022,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4997999966144562},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4648999869823456},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4311999976634979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4124000072479248},{"id":"https://openalex.org/keywords/gaussian-random-field","display_name":"Gaussian random field","score":0.3806000053882599},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.3476000130176544},{"id":"https://openalex.org/keywords/approximation-theory","display_name":"Approximation theory","score":0.34439998865127563}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175999999046326},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4837999939918518},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45570001006126404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4544999897480011},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4311999976634979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C51267290","wikidata":"https://www.wikidata.org/wiki/Q5527848","display_name":"Gaussian random field","level":4,"score":0.3806000053882599},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3230000138282776},{"id":"https://openalex.org/C2988922011","wikidata":"https://www.wikidata.org/wiki/Q5449244","display_name":"Filtering theory","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.25220000743865967},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3674120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3674120","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41824332","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41824332","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1199464621","display_name":null,"funder_award_id":"L257002","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Practical":[0],"Bayes":[1],"filters":[2,29,264],"often":[3],"assume":[4],"the":[5,20,60,91,95,100,105,119,125,129,140,149,153,157,172,177,180,191,222,231,278],"state":[6],"distribution":[7],"of":[8,65,104,123,151,179],"each":[9,227],"time":[10,228,254],"step":[11,97,113,186],"to":[12,70,80,111,127,137,144,170,221,261],"be":[13],"Gaussian":[14,22,28,66,158,206,224,263],"for":[15,94,176,200,212,238],"computational":[16,291],"tractability,":[17],"resulting":[18],"in":[19,114,190],"so-called":[21],"filters.":[23,117],"When":[24],"facing":[25],"nonlinear":[26,201],"systems,":[27],"such":[30,265],"as":[31,68,266],"extended":[32],"Kalman":[33,38],"filter":[34,39,199,211,218,276],"(EKF)":[35],"or":[36,209],"unscented":[37],"(UKF)":[40],"typically":[41],"rely":[42],"on":[43,156],"certain":[44],"linearization":[45,146,273],"techniques,":[46],"which":[47,108],"can":[48],"introduce":[49,195],"large":[50],"estimation":[51,232],"errors.":[52,147],"To":[53],"address":[54],"this":[55,57,184],"issue,":[56],"paper":[58],"reconstructs":[59],"prediction":[61,96,192],"and":[62,243,271],"update":[63,120,141,185],"steps":[64],"filtering":[67],"solutions":[69],"two":[71,102],"distinct":[72],"optimization":[73],"problems,":[74],"whose":[75],"optimal":[76,223],"conditions":[77],"are":[78],"found":[79],"have":[81],"analytical":[82],"forms":[83],"from":[84],"Stein's":[85],"lemma.":[86],"It":[87],"is":[88,109,234],"observed":[89],"that":[90,112,165,216],"stationary":[92,130],"point":[93],"requires":[98],"calculating":[99],"first":[101],"moments":[103],"prior":[106],"distribution,":[107],"equivalent":[110],"existing":[115],"moment-matching":[116],"In":[118],"step,":[121,193],"instead":[122],"linearizing":[124],"model":[126],"approximate":[128],"points,":[131],"we":[132,160,194],"propose":[133],"an":[134],"iterative":[135,198],"approach":[136],"directly":[138],"minimize":[139],"step's":[142],"objective":[143],"avoid":[145],"For":[148],"purpose":[150],"performing":[152],"steepest":[154],"descent":[155],"manifold,":[159],"derive":[161],"its":[162],"natural":[163],"gradient":[164,173],"leverages":[166],"Fisher":[167],"information":[168],"matrix":[169],"adjust":[171],"direction,":[174],"accounting":[175],"curvature":[178],"parameter":[181],"space.":[182],"Combining":[183],"with":[187],"moment":[188],"matching":[189],"a":[196,249,289],"new":[197],"systems":[202],"called":[203],"Natural":[204],"Gradient":[205],"Approximation":[207],"filter,":[208,274],"NANO":[210,217,275],"short.":[213],"We":[214],"prove":[215],"locally":[219],"converges":[220],"approximation":[225],"at":[226],"step.":[229],"Furthermore,":[230],"error":[233,283],"proven":[235],"exponentially":[236],"bounded":[237],"nearly":[239],"linear":[240],"measurement":[241],"equation":[242],"low":[244],"noise":[245],"levels":[246],"through":[247],"constructing":[248],"supermartingale-like":[250],"property":[251],"across":[252],"consecutive":[253],"steps.":[255],"Real-world":[256],"experiments":[257],"demonstrate":[258],"that,":[259],"compared":[260],"popular":[262],"EKF,":[267,270],"UKF,":[268],"iterated":[269],"posterior":[272],"reduces":[277],"average":[279],"root":[280],"mean":[281],"square":[282],"by":[284],"approximately":[285],"45%":[286],"while":[287],"maintaining":[288],"comparable":[290],"burden.":[292]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-03-14T00:00:00"}