{"id":"https://openalex.org/W7220977376","doi":"https://doi.org/10.48550/arxiv.2610.09813","title":"Drift Estimation for a Multi-Dimensional L\u00e9vy-Driven Stochastic Differential Equation Using Deep Neural Networks","display_name":"Drift Estimation for a Multi-Dimensional L\u00e9vy-Driven Stochastic Differential Equation Using Deep Neural Networks","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220977376","doi":"https://doi.org/10.48550/arxiv.2610.09813"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09813","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09813","pdf_url":"https://arxiv.org/pdf/2610.09813","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157938161","display_name":"Taisei Noguchi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noguchi, Taisei","raw_affiliation_strings":["Graduate School of Information Science and Technology , The University of Tokyo , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology , The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046373297","display_name":"Teppei Ogihara","orcid":"https://orcid.org/0000-0003-0839-9733","observed_orcids":["https://orcid.org/0000-0003-0839-9733"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ogihara, Teppei","raw_affiliation_strings":["Graduate School of Information Science and Technology , The University of Tokyo , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology , The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10067","display_name":"Stochastic processes and financial applications","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/drift-estimation","display_name":"drift estimation","score":0.8679999709129333},{"id":"https://openalex.org/keywords/levy-driven-stochastic-differential-equations","display_name":"L\u00e9vy-driven stochastic differential equations","score":0.9559999704360962},{"id":"https://openalex.org/keywords/nonparametric-estimation","display_name":"nonparametric estimation","score":0.7910000085830688},{"id":"https://openalex.org/keywords/oracle-inequalities","display_name":"oracle inequalities","score":0.7089999914169312},{"id":"https://openalex.org/keywords/least-squares-estimator","display_name":"least squares estimator","score":0.847000002861023},{"id":"https://openalex.org/keywords/minimax-lower-bounds","display_name":"minimax lower bounds","score":0.7670000195503235},{"id":"https://openalex.org/keywords/minimax-optimality","display_name":"minimax optimality","score":0.9160000085830688}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7578999996185303},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.7149999737739563},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6816999912261963},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C48406656","wikidata":"https://www.wikidata.org/wiki/Q534112","display_name":"Martingale (probability theory)","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5687999725341797},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C39943821","wikidata":"https://www.wikidata.org/wiki/Q506346","display_name":"Semimartingale","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C57945734","wikidata":"https://www.wikidata.org/wiki/Q7977941","display_name":"Weak convergence","level":3,"score":0.41510000824928284},{"id":"https://openalex.org/C2776825372","wikidata":"https://www.wikidata.org/wiki/Q3922411","display_name":"Jump process","level":3,"score":0.41339999437332153},{"id":"https://openalex.org/C27851653","wikidata":"https://www.wikidata.org/wiki/Q829653","display_name":"Bounded variation","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C88757350","wikidata":"https://www.wikidata.org/wiki/Q1557613","display_name":"L\u00e9vy process","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C133338972","wikidata":"https://www.wikidata.org/wiki/Q2055750","display_name":"Compound Poisson process","level":4,"score":0.29269999265670776},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C157709441","wikidata":"https://www.wikidata.org/wiki/Q1411887","display_name":"Uniform convergence","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C104824951","wikidata":"https://www.wikidata.org/wiki/Q830124","display_name":"Girsanov theorem","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C3098717","wikidata":"https://www.wikidata.org/wiki/Q1144872","display_name":"Modulus of continuity","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09813","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09813","pdf_url":"https://arxiv.org/pdf/2610.09813","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.09813","doi":"https://doi.org/10.48550/arxiv.2610.09813","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09813","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.09813","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09813","pdf_url":"https://arxiv.org/pdf/2610.09813","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220977376.pdf","grobid_xml":"https://content.openalex.org/works/W7220977376.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2298174650","https://openalex.org/W4387807337","https://openalex.org/W7134259851","https://openalex.org/W7123529923","https://openalex.org/W4388514273","https://openalex.org/W4415340116","https://openalex.org/W7135224239","https://openalex.org/W4410645674","https://openalex.org/W2748085134","https://openalex.org/W7208585355"],"abstract_inverted_index":{"We":[0,75],"develop":[1],"a":[2,142,147],"non-asymptotic":[3],"theory":[4],"for":[5,38,88],"nonparametric":[6],"drift":[7,116],"estimation":[8],"in":[9,134],"discretely":[10],"observed":[11,82],"multi-dimensional":[12],"L\u00e9vy-driven":[13],"stochastic":[14],"differential":[15],"equations":[16],"using":[17,84],"sparse":[18],"ReLU":[19],"neural":[20],"networks.":[21],"Under":[22],"exponential":[23],"\\(\u03b2\\)-mixing":[24],"and":[25,50,92],"an":[26,35,85],"exponential-tail":[27],"condition":[28],"on":[29,146],"the":[30,39,47,51,66,81,95,98,107,111,154,160],"L\u00e9vy":[31],"measure,":[32],"we":[33,140],"establish":[34,141],"oracle":[36],"inequality":[37],"least-squares":[40],"estimator.":[41],"The":[42,127],"jump":[43,131],"component":[44],"changes":[45],"both":[46],"martingale":[48],"structure":[49],"concentration":[52],"regime":[53],"relative":[54],"to":[55,104,166],"diffusion":[56,113],"models:":[57],"continuous":[58],"martingales":[59],"are":[60,70],"replaced":[61],"by":[62],"discontinuous":[63],"martingales,":[64],"while":[65],"relevant":[67],"empirical-process":[68],"fluctuations":[69],"sub-exponential":[71],"rather":[72],"than":[73],"sub-Gaussian.":[74],"handle":[76],"these":[77],"difficulties":[78],"without":[79],"truncating":[80],"increments,":[83],"exponential-supermartingale":[86],"argument":[87],"compensated":[89],"Poisson":[90],"integrals":[91],"\\(\u03c8_1\\)-chaining.":[93],"Despite":[94],"weaker":[96],"concentration,":[97],"resulting":[99],"statistical":[100],"bound":[101,145],"is,":[102],"up":[103,165],"constants,":[105],"of":[106],"same":[108],"order":[109],"as":[110],"corresponding":[112],"bound.":[114],"For":[115],"functions":[117],"with":[118,153],"hierarchical":[119],"compositional":[120],"structure,":[121],"this":[122,157],"yields":[123],"intrinsic-dimensional":[124],"convergence":[125],"rates.":[126],"framework":[128],"allows":[129],"infinite":[130,137],"activity":[132],"and,":[133],"some":[135],"cases,":[136],"variation.":[138],"Finally,":[139],"minimax":[143,163],"lower":[144],"fixed":[148],"non-trivial":[149],"compound-Poisson":[150],"submodel.":[151],"Together":[152],"upper":[155],"bound,":[156],"shows":[158],"that":[159],"estimator":[161],"is":[162],"optimal":[164],"logarithmic":[167],"factors.":[168]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-09T00:00:00"}