{"id":"https://openalex.org/W7166190594","doi":"https://doi.org/10.48550/arxiv.2606.27298","title":"Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity","display_name":"Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166190594","doi":"https://doi.org/10.48550/arxiv.2606.27298"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.27298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27298","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":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.2606.27298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017956500","display_name":"Haitong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136473496","display_name":"Deepak Narayanan Sridharan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sridharan, Deepak Narayanan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089128021","display_name":"David Steurer","orcid":"https://orcid.org/0000-0002-3908-8180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steurer, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076325451","display_name":"Manuel Wiedmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wiedmer, Manuel","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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.2840999960899353,"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":0.2840999960899353,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1981000006198883,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.07800000160932541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6729999780654907},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.6347000002861023},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4659999907016754},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4584999978542328},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.44040000438690186},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.4090999960899353},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.392300009727478},{"id":"https://openalex.org/keywords/truncation-error","display_name":"Truncation error","score":0.37959998846054077}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7371000051498413},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6729999780654907},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.6347000002861023},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5985999703407288},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4584999978542328},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C104942944","wikidata":"https://www.wikidata.org/wiki/Q3434686","display_name":"Truncation error","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2777630202","wikidata":"https://www.wikidata.org/wiki/Q5527840","display_name":"Gaussian measure","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C51267290","wikidata":"https://www.wikidata.org/wiki/Q5527848","display_name":"Gaussian random field","level":4,"score":0.26499998569488525},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.27298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27298","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.27298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27298","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,22,67,87,91,136,140,156,159,173],"fundamental":[3],"problem":[4],"of":[5,89,105,135,139,145,158],"learning":[6,186],"a":[7,118,132,146],"high-dimensional":[8],"Gaussian":[9,69,119,142,161],"truncated":[10,141],"to":[11,70,171],"an":[12,56],"unknown":[13],"halfspace.":[14],"Lee,":[15],"Mehrotra":[16],"and":[17,34,51,65,98,107,162],"Zampetakis":[18],"(FOCS'24)":[19],"recently":[20],"obtained":[21],"first":[23],"polynomial":[24],"time":[25,35,99,174],"algorithm":[26,58,78],"for":[27,44,123],"this":[28,113],"problem,":[29],"but":[30],"their":[31],"resulting":[32],"sample":[33,97],"complexity":[36,100],"bounds":[37],"are":[38,101],"not":[39],"optimal.":[40],"Under":[41],"non-trivial":[42],"truncation,":[43],"any":[45],"target":[46],"accuracy":[47],"$\\varepsilon":[48],">":[49],"0$":[50],"dimension":[52],"$d$":[53,106],"we":[54,115],"give":[55],"efficient":[57],"that":[59,181],"uses":[60],"$n":[61],"=":[62],"\\tilde{O}(d^2/\\varepsilon^2)$":[63],"samples":[64],"learns":[66],"underlying":[68],"error":[71],"$\\varepsilon$":[72,108],"in":[73,103,112,143,185],"total":[74],"variation":[75],"distance.":[76],"Our":[77],"is":[79,84,131,182],"also":[80],"fast:":[81],"its":[82],"runtime":[83],"dominated":[85],"by":[86],"cost":[88],"computing":[90],"empirical":[92],"covariance":[93],"matrix.":[94],"Both":[95],"our":[96,129],"optimal":[102],"terms":[104,144],"even":[109],"without":[110],"truncation:":[111],"regard,":[114],"can":[116],"learn":[117],"under":[120,187],"halfspace":[121],"truncation":[122,148,152],"free.":[124],"The":[125],"key":[126],"ingredient":[127],"behind":[128],"result":[130],"novel":[133],"reinterpretation":[134,168],"low-degree":[137],"moments":[138],"relative":[147,151],"parameter.":[149],"This":[150,167],"parameter":[153,165],"uniquely":[154],"determines":[155],"parameters":[157],"untruncated":[160],"enables":[163],"direct":[164],"recovery.":[166],"allows":[169],"us":[170],"circumvent":[172],"intensive":[175],"projected":[176],"stochastic":[177],"gradient":[178],"descent":[179],"procedure":[180],"widely":[183],"used":[184],"truncation.":[188]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-27T00:00:00"}