{"id":"https://openalex.org/W755406177","doi":null,"title":"Efficient Sampling for Gaussian Graphical Models via Spectral Sparsification","display_name":"Efficient Sampling for Gaussian Graphical Models via Spectral Sparsification","publication_year":2015,"publication_date":"2015-06-26","ids":{"openalex":"https://openalex.org/W755406177","mag":"755406177"},"language":"en","primary_location":{"id":"mag:755406177","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v40/Cheng15.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418075","display_name":"Conference on Learning Theory","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Learning Theory","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5085968832","display_name":"Dehua Cheng","orcid":"https://orcid.org/0000-0002-6177-9834","observed_orcids":["https://orcid.org/0000-0002-6177-9834"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dehua Cheng","raw_affiliation_strings":["University of Southern California, Los Angeles, United States"],"raw_orcid":"https://orcid.org/0000-0002-6177-9834","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026746295","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0002-0019-2570","observed_orcids":["https://orcid.org/0000-0002-0019-2570","https://orcid.org/0000-0003-0162-5902"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Cheng","raw_affiliation_strings":["University of Southern California, Los Angeles, United States"],"raw_orcid":"https://orcid.org/0000-0002-0019-2570","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351175","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0002-7055-9518","observed_orcids":["https://orcid.org/0000-0002-7055-9518","https://orcid.org/0000-0003-4242-4840"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["University of Southern California, Los Angeles, United States"],"raw_orcid":"https://orcid.org/0000-0003-4242-4840","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112534230","display_name":"Richard Peng","orcid":"https://orcid.org/0000-0002-5407-7965","observed_orcids":["https://orcid.org/0000-0002-5407-7965"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Peng","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102005063","display_name":"Shang\u2010Hua Teng","orcid":"https://orcid.org/0000-0001-5011-4514","observed_orcids":["https://orcid.org/0000-0001-5011-4514"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shang\u2010Hua Teng","raw_affiliation_strings":["University of Southern California, Los Angeles, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8569,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91421144,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"364","last_page":"390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.5946999788284302,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.5946999788284302,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.17419999837875366,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.13760000467300415,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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-graphical-models","display_name":"Gaussian graphical models","score":0.9010000228881836},{"id":"https://openalex.org/keywords/spectral-sparsification","display_name":"spectral sparsification","score":0.9670000076293945},{"id":"https://openalex.org/keywords/gaussian-sampling","display_name":"Gaussian sampling","score":0.6890000104904175},{"id":"https://openalex.org/keywords/laplacian-matrix","display_name":"Laplacian matrix","score":0.8389999866485596},{"id":"https://openalex.org/keywords/symmetric-diagonally-dominant-matrices","display_name":"symmetric diagonally dominant matrices","score":0.828000009059906},{"id":"https://openalex.org/keywords/precision-matrix","display_name":"precision matrix","score":0.5400000214576721},{"id":"https://openalex.org/keywords/nearly-linear-time-algorithms","display_name":"near-linear time algorithms","score":0.7910000085830688},{"id":"https://openalex.org/keywords/simultaneous-sampling","display_name":"synchronous sampling","score":0.6069999933242798},{"id":"https://openalex.org/keywords/multilevel-methods","display_name":"multilevel methods","score":0.7799999713897705},{"id":"https://openalex.org/keywords/polynomial-matrices","display_name":"matrix polynomials","score":0.7149999737739563},{"id":"https://openalex.org/keywords/spectral-graph-theory","display_name":"spectral graph theory","score":0.6549999713897705},{"id":"https://openalex.org/keywords/reversible-markov-chains","display_name":"reversible Markov chains","score":0.9380000233650208}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6090789437294006},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5637562870979309},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4771568179130554},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41460418701171875},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3237549662590027},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:755406177","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v40/Cheng15.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418075","display_name":"Conference on Learning Theory","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Learning Theory","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W3401598","https://openalex.org/W31207775","https://openalex.org/W114565888","https://openalex.org/W585133165","https://openalex.org/W1663973292","https://openalex.org/W1746680969","https://openalex.org/W1783195972","https://openalex.org/W1916091028","https://openalex.org/W1979505770","https://openalex.org/W1983193888","https://openalex.org/W2045107949","https://openalex.org/W2073647817","https://openalex.org/W2079746361","https://openalex.org/W2079853639","https://openalex.org/W2083202936","https://openalex.org/W2084813411","https://openalex.org/W2098983955","https://openalex.org/W2103133389","https://openalex.org/W2118918399","https://openalex.org/W2129027292","https://openalex.org/W2129575457","https://openalex.org/W2131297510","https://openalex.org/W2135194391","https://openalex.org/W2138243089","https://openalex.org/W2153441719","https://openalex.org/W2164853353","https://openalex.org/W2395355800","https://openalex.org/W2951006135"],"related_works":["https://openalex.org/W1714536202","https://openalex.org/W4385694543","https://openalex.org/W2375314448","https://openalex.org/W61776329","https://openalex.org/W1676380800","https://openalex.org/W2950512243","https://openalex.org/W2526826214","https://openalex.org/W2135927639","https://openalex.org/W7024361774","https://openalex.org/W2605384476"],"abstract_inverted_index":{"Motivated":[0],"by":[1],"a":[2,12,19,71,82,180],"sampling":[3,110],"problem":[4],"basic":[5,60],"to":[6,81,103,146,242],"computational":[7],"statistical":[8],"inference,":[9],"we":[10,49],"develop":[11],"toolset":[13],"based":[14,175],"on":[15,34,176,214,221],"spectral":[16,46,97,167,227,250],"sparsification":[17,168,198,228],"for":[18,57,122,200,230],"family":[20],"of":[21,160,166,182,206,254],"fundamental":[22],"problems":[23],"involving":[24],"Gaussian":[25,38,123,144,151],"sampling,":[26],"matrix":[27,61,68,232],"functionals,":[28],"and":[29,41,70,120,139,188,249,263],"reversible":[30],"Markov":[31],"chains.":[32],"Drawing":[33],"the":[35,42,51,58,107,215,218,244,255],"connection":[36,245],"between":[37,246],"graphical":[39],"models":[40],"recent":[43],"breakthroughs":[44],"in":[45,117,154,259],"graph":[47,251],"theory,":[48,252],"give":[50,196],"first":[52,108,210],"nearly":[53,136,224],"linear":[54,86,137,225],"time":[55,226],"algorithm":[56,111,229],"following":[59],"problem:":[62],"Given":[63],"an":[64,148,164],"n\u00d7":[65,84],"n":[66,85],"Laplacian":[67],"M":[69,91,178],"constant":[72],"\u22121":[73],"\u2264":[74,76],"p":[75,100],"1,":[77],"provide":[78],"efficient":[79],"access":[80],"sparse":[83,193],"operator":[87],"C":[88],"such":[89],"that":[90,112,203],"\u2248":[92,95],"CC>,":[93],"where":[94],"denotes":[96],"similarity.":[98],"When":[99],"is":[101,113,163],"set":[102],"\u22121,":[104],"this":[105,201],"gives":[106],"parallel":[109],"essentially":[114],"optimal":[115],"both":[116],"total":[118],"work":[119,138],"randomness":[121],"random":[124,142,152],"fields":[125,258],"with":[126,169,192],"symmetric":[127],"diagonally":[128],"dominant":[129],"(SDD)":[130],"precision":[131],"matrices.":[132],"It":[133],"only":[134],"requires":[135],"2n":[140],"i.i.d.":[141,150],"univariate":[143],"samples":[145],"generate":[147],"n-dimensional":[149],"sample":[153],"polylogarithmic":[155],"depth.":[156],"The":[157,209],"key":[158],"ingredient":[159],"our":[161,222],"approach":[162,202],"integration":[165],"multilevel":[170],"method:":[171],"Our":[172],"algorithms":[173],"are":[174],"factoring":[177],"into":[179],"product":[181],"well-conditioned":[183],"matrices,":[184],"then":[185],"introducing":[186],"powers":[187],"replacing":[189],"dense":[190],"matrices":[191],"approximations.":[194],"We":[195,234],"two":[197,253],"methods":[199],"may":[204],"be":[205],"independent":[207],"interest.":[208],"invokes":[211],"Maclaurin":[212],"series":[213],"factors,":[216],"while":[217],"second":[219],"builds":[220],"new":[223],"random-walk":[231],"polynomials.":[233],"expect":[235],"these":[236],"algorithmic":[237],"advances":[238],"will":[239],"also":[240],"help":[241],"strengthen":[243],"machine":[247],"learning":[248],"most":[256],"active":[257],"understanding":[260],"large":[261],"data":[262],"networks.":[264]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}