{"id":"https://openalex.org/W4417294949","doi":"https://doi.org/10.48550/arxiv.2512.10188","title":"The Interplay of Statistics and Noisy Optimization: Learning Linear Predictors with Random Data Weights","display_name":"The Interplay of Statistics and Noisy Optimization: Learning Linear Predictors with Random Data Weights","publication_year":2025,"publication_date":"2025-12-11","ids":{"openalex":"https://openalex.org/W4417294949","doi":"https://doi.org/10.48550/arxiv.2512.10188"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.10188","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10188","pdf_url":"https://arxiv.org/pdf/2512.10188","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.10188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087202335","display_name":"Gabriel Clara","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Clara, Gabriel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120791565","display_name":"Yazan Mash'al","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mash'al, Yazan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087202335"],"corresponding_institution_ids":[],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9787999987602234,"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":0.9787999987602234,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.004999999888241291,"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/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/weighting","display_name":"Weighting","score":0.767300009727478},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5361999869346619},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5353000164031982},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5163000226020813},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4507000148296356},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.44449999928474426},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4244999885559082},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4133000075817108},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.40549999475479126}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.767300009727478},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5600000023841858},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5361999869346619},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4244999885559082},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39739999175071716},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C200985842","wikidata":"https://www.wikidata.org/wiki/Q3375503","display_name":"Random permutation","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C95763700","wikidata":"https://www.wikidata.org/wiki/Q578985","display_name":"Convergence of random variables","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.10188","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10188","pdf_url":"https://arxiv.org/pdf/2512.10188","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.10188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.10188","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.10188","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10188","pdf_url":"https://arxiv.org/pdf/2512.10188","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417294949.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,57],"analyze":[1,45],"gradient":[2,25],"descent":[3],"with":[4,35,69],"randomly":[5],"weighted":[6,70],"data":[7],"points":[8],"in":[9,79],"a":[10,15,41],"linear":[11,71],"regression":[12],"model,":[13],"under":[14],"generic":[16],"weighting":[17,33,109],"distribution.":[18],"This":[19],"includes":[20],"various":[21,49],"forms":[22],"of":[23,48,51,108,120],"stochastic":[24],"descent,":[26],"importance":[27],"sampling,":[28],"but":[29],"also":[30,89],"extends":[31],"to":[32,44,134],"distributions":[34],"arbitrary":[36],"continuous":[37],"values,":[38],"thereby":[39],"providing":[40],"unified":[42],"framework":[43],"the":[46,54,59,64,91,96,113,121],"impact":[47],"kinds":[50],"noise":[52],"on":[53,100],"training":[55],"trajectory.":[56],"characterize":[58],"implicit":[60],"regularization":[61],"induced":[62,94],"through":[63],"random":[65],"weighting,":[66],"connect":[67],"it":[68],"regression,":[72],"and":[73,81,117],"derive":[74],"non-asymptotic":[75],"bounds":[76],"for":[77,129],"convergence":[78,136],"first":[80],"second":[82],"moments.":[83],"Leveraging":[84],"geometric":[85],"moment":[86],"contraction,":[87],"we":[88,103],"investigate":[90],"stationary":[92],"distribution":[93,110],"by":[95],"added":[97],"noise.":[98],"Based":[99],"these":[101],"results,":[102],"discuss":[104],"how":[105],"specific":[106],"choices":[107],"influence":[111],"both":[112],"underlying":[114],"optimization":[115],"problem":[116],"statistical":[118,139],"properties":[119],"resulting":[122],"estimator,":[123],"as":[124,126],"well":[125],"some":[127],"examples":[128],"which":[130],"weightings":[131],"that":[132],"lead":[133],"fast":[135],"cause":[137],"bad":[138],"performance.":[140]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-12-13T00:00:00"}