{"id":"https://openalex.org/W7220895166","doi":"https://doi.org/10.48550/arxiv.2610.09166","title":"Lower Bounds for Parallel Diffusion Sampling","display_name":"Lower Bounds for Parallel Diffusion Sampling","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220895166","doi":"https://doi.org/10.48550/arxiv.2610.09166"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09166","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09166","pdf_url":"https://arxiv.org/pdf/2610.09166","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070754002","display_name":"Yiwen Kou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kou, Yiwen","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157929884","display_name":"Yimeng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Yimeng","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.7695000171661377,"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"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.7695000171661377,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.054499998688697815,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.033799998462200165,"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/diffusive-sampling","display_name":"diffusion sampling","score":0.8190000057220459},{"id":"https://openalex.org/keywords/simultaneous-sampling","display_name":"synchronous sampling","score":0.6299999952316284},{"id":"https://openalex.org/keywords/lower-bounds","display_name":"lower bounds","score":0.8809999823570251},{"id":"https://openalex.org/keywords/score-based-generative-models","display_name":"score-based generative models","score":0.5889999866485596},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.7910000085830688},{"id":"https://openalex.org/keywords/axis-aligned-boxes","display_name":"axis-aligned boxes","score":0.8920000195503235},{"id":"https://openalex.org/keywords/randomized-algorithms","display_name":"randomized algorithms","score":0.6389999985694885},{"id":"https://openalex.org/keywords/serial-dependence","display_name":"serial dependence","score":0.6669999957084656},{"id":"https://openalex.org/keywords/computational-complexity","display_name":"computational complexity","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7060999870300293},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6697999835014343},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6473000049591064},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5789999961853027},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49779999256134033},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C63553672","wikidata":"https://www.wikidata.org/wiki/Q581168","display_name":"Binary logarithm","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C86426650","wikidata":"https://www.wikidata.org/wiki/Q7452504","display_name":"Sequential estimation","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09166","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09166","pdf_url":"https://arxiv.org/pdf/2610.09166","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.2610.09166","doi":"https://doi.org/10.48550/arxiv.2610.09166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09166","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.09166","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09166","pdf_url":"https://arxiv.org/pdf/2610.09166","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":[{"id":"https://openalex.org/G1643764941","display_name":"Collaborative Research: CCF: AF: Small: New Frontiers in Structures vs Randomness with Applications to Combinatorics, Complexity, Algorithms","funder_award_id":"2425350","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6037617637","display_name":"Collaborative Research: EnCORE: Institute for Emerging CORE Methods in Data Science","funder_award_id":"2217033","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220895166.pdf","grobid_xml":"https://content.openalex.org/works/W7220895166.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W7213577207","https://openalex.org/W7214403325"],"related_works":["https://openalex.org/W7154273332","https://openalex.org/W4399400064","https://openalex.org/W4416189886","https://openalex.org/W4405262738","https://openalex.org/W7204176442","https://openalex.org/W4415800709","https://openalex.org/W7124453196","https://openalex.org/W7221532418","https://openalex.org/W7213577207","https://openalex.org/W7129339926"],"abstract_inverted_index":{"Standard":[0],"diffusion":[1,60],"samplers":[2,21],"generate":[3],"samples":[4],"through":[5],"sequential":[6],"evaluations":[7],"of":[8,59,140],"a":[9,66,74,88],"learned":[10],"score":[11,30,126,166],"function,":[12],"with":[13,62,124,160,199],"each":[14,42,171,189],"query":[15],"depending":[16],"on":[17,55,174],"previous":[18],"answers.":[19],"Parallel":[20],"seek":[22],"to":[23],"accelerate":[24],"this":[25],"process":[26],"by":[27],"making":[28,112],"multiple":[29],"queries":[31,115],"simultaneously.":[32],"We":[33,48,152],"ask":[34],"how":[35],"many":[36,46,114],"adaptive":[37],"rounds":[38],"are":[39],"necessary":[40],"when":[41],"round":[43,57,117,190],"allows":[44],"polynomially":[45,113],"queries.":[47],"establish":[49],"the":[50,56,102,137,181],"first":[51],"polynomial":[52],"lower":[53,76,91,142],"bounds":[54,106,143],"complexity":[58],"sampling":[61,79,95,150],"approximate":[63,165],"scores":[64],"satisfying":[65],"mean-square":[67],"accuracy":[68],"guarantee.":[69],"Specifically,":[70],"we":[71],"prove":[72],"(1)":[73],"$\\widetilde\u03a9(d^{1/3})$-round":[75],"bound":[77,92],"for":[78,93,108,144],"smooth,":[80],"near-isotropic":[81,134],"Gaussian":[82],"mixtures":[83],"in":[84,101,170,177],"$\\mathbb{R}^d$,":[85],"and":[86,121,128,148,163,184],"(2)":[87],"tight":[89],"$\u03a9(d)$-round":[90],"uniform":[94],"from":[96],"anisotropic":[97],"axis-aligned":[98],"boxes":[99],"contained":[100],"unit":[103],"ball.":[104],"Both":[105],"hold":[107],"arbitrary":[109,119],"randomized":[110],"algorithms":[111],"per":[116],"at":[118,194],"locations":[120],"noise":[122],"levels,":[123],"inverse-polynomial":[125],"error":[127],"constant":[129],"total":[130],"variation":[131],"accuracy.":[132],"Our":[133],"construction":[135],"follows":[136],"blockwise":[138],"approach":[139],"earlier":[141,178],"parallel":[145],"matroid":[146],"search":[147],"discrete":[149],"\\cite{KUW85,AGR24}.":[151],"use":[153],"independent":[154],"coordinate":[155],"blocks":[156],"containing":[157],"random":[158],"codebooks":[159],"well-separated":[161],"rates":[162],"construct":[164],"oracles":[167],"whose":[168],"responses":[169],"block":[172,198],"depend":[173],"consistency":[175],"tests":[176,186],"blocks.":[179],"Together,":[180],"rate":[182],"separation":[183],"these":[185],"ensure":[187],"that":[188],"reveals":[191],"information":[192],"about":[193],"most":[195],"one":[196],"additional":[197],"high":[200],"probability.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}