{"id":"https://openalex.org/W7160959157","doi":"https://doi.org/10.48550/arxiv.2605.10237","title":"The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently","display_name":"The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160959157","doi":"https://doi.org/10.48550/arxiv.2605.10237"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10237","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.10237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004244752","display_name":"Elisabetta Cornacchia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cornacchia, Elisabetta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135982994","display_name":"Dan Mikulincer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikulincer, Dan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135930195","display_name":"Elchanan Mossel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mossel, Elchanan","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8920000195503235,"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":0.8920000195503235,"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":0.03009999915957451,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.02590000070631504,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.765500009059906},{"id":"https://openalex.org/keywords/random-walk","display_name":"Random walk","score":0.6359999775886536},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.44600000977516174},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4156000018119812},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.39489999413490295},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3935999870300293}],"concepts":[{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.765500009059906},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.6359999775886536},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4796000123023987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47369998693466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43070000410079956},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C119322782","wikidata":"https://www.wikidata.org/wiki/Q2662236","display_name":"VC dimension","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10237","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10237","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.43508076667785645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,41],"study":[1],"how":[2],"temporal":[3,64,120],"correlations":[4,121],"in":[5,101],"the":[6,48,58,63,94,102,125],"data":[7],"can":[8,66],"make":[9],"certain":[10],"sparse":[11,27],"learning":[12,28],"problems":[13],"efficiently":[14],"learnable":[15],"by":[16,52,69],"gradient-based":[17,35],"methods.":[18],"Our":[19],"focus":[20],"is":[21,98],"on":[22,57],"Boolean":[23],"k-juntas,":[24],"a":[25,53,70,78],"canonical":[26],"problem":[29],"known":[30],"to":[31],"pose":[32],"barriers":[33],"for":[34,111],"methods":[36,114],"under":[37],"independent":[38],"uniform":[39],"samples.":[40,89],"show":[42,109],"that":[43,110],"this":[44,61],"picture":[45],"changes":[46],"when":[47],"samples":[49],"are":[50],"generated":[51],"lazy":[54],"random":[55],"walk":[56],"hypercube.":[59],"In":[60],"setting,":[62],"dependencies":[65],"be":[67],"exploited":[68],"two-layer":[71],"ReLU":[72],"network":[73],"trained":[74],"using":[75,115],"stylized-SGD":[76],"with":[77],"temporal-difference":[79],"loss,":[80],"which":[81],"compares":[82],"target":[83],"and":[84],"predicted":[85],"increments":[86],"across":[87],"consecutive":[88],"For":[90],"every":[91],"fixed":[92],"k,":[93],"resulting":[95],"sample":[96],"complexity":[97],"essentially":[99],"linear":[100],"ambient":[103],"dimension":[104],"d.":[105],"By":[106],"contrast,":[107],"we":[108],"large-batch":[112],"gradient":[113],"standard":[116],"convex":[117],"pointwise":[118],"losses,":[119],"do":[122],"not":[123],"provide":[124],"same":[126],"advantage.":[127]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}