{"id":"https://openalex.org/W7129339926","doi":"https://doi.org/10.48550/arxiv.2602.15008","title":"Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees","display_name":"Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129339926","doi":"https://doi.org/10.48550/arxiv.2602.15008"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.15008","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009956299","display_name":"Daniil Dmitriev","orcid":"https://orcid.org/0000-0002-3241-5599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitriev, Daniil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115593884","display_name":"Zhihan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zhihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070760994","display_name":"Yuting Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Yuting","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20416254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6617000102996826,"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":0.6617000102996826,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.13420000672340393,"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/T11885","display_name":"MRI in cancer diagnosis","score":0.018300000578165054,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.635200023651123},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5809999704360962},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5561000108718872},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4715000092983246},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4578999876976013},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.42750000953674316},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4251999855041504},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.39579999446868896},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.38260000944137573}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6570000052452087},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.635200023651123},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4251999855041504},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42179998755455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38600000739097595},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C157709441","wikidata":"https://www.wikidata.org/wiki/Q1411887","display_name":"Uniform convergence","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25999999046325684},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.25220000743865967},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C75438885","wikidata":"https://www.wikidata.org/wiki/Q3403615","display_name":"Large deviations theory","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.15008","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.15008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15008","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":"pmh:doi:10.48550/arxiv.2602.15008","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Diffusion":[0],"models":[1,29],"over":[2],"discrete":[3,27,65,129],"spaces":[4],"have":[5],"recently":[6],"shown":[7],"striking":[8],"empirical":[9],"success,":[10],"yet":[11],"their":[12],"theoretical":[13],"foundations":[14],"remain":[15],"incomplete.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20,67,108,131],"study":[21],"the":[22,70,83,87,94,120,148,172,212,218],"sampling":[23],"efficiency":[24],"of":[25,77,86,105,217],"score-based":[26],"diffusion":[28],"under":[30],"a":[31,38,103,110,133,170],"continuous-time":[32],"Markov":[33,196],"chain":[34],"(CTMC)":[35],"formulation,":[36],"with":[37,81],"focus":[39],"on":[40,93,119,211],"$\u03c4$-leaping-based":[41],"samplers.":[42],"We":[43],"establish":[44,109],"sharp":[45],"convergence":[46,138,187],"guarantees":[47],"for":[48,56,166,189],"attaining":[49],"$\\varepsilon$":[50],"accuracy":[51],"in":[52,125],"Kullback-Leibler":[53],"(KL)":[54],"divergence":[55],"both":[57],"uniform":[58,64],"and":[59,98,200],"masking":[60,128],"noising":[61],"processes.":[62],"For":[63,127],"diffusion,":[66,130],"show":[68],"that":[69,116],"$\u03c4$-leaping":[71,135],"algorithm":[72],"achieves":[73],"an":[74,143],"iteration":[75],"complexity":[76],"order":[78],"$\\tilde":[79],"O(d/\\varepsilon)$,":[80],"$d$":[82],"ambient":[84,121],"dimension":[85,122],"target":[88],"distribution,":[89],"eliminating":[90],"linear":[91,117],"dependence":[92,118],"vocabulary":[95],"size":[96],"$S$":[97],"improving":[99],"existing":[100],"bounds":[101],"by":[102,142,155],"factor":[104],"$d$;":[106],"moreover,":[107],"matching":[111],"algorithmic":[112,183],"lower":[113],"bound":[114],"showing":[115],"is":[123,140,153],"unavoidable":[124],"general.":[126],"introduce":[132],"modified":[134],"sampler":[136,173],"whose":[137],"rate":[139],"governed":[141],"intrinsic":[144],"information-theoretic":[145],"quantity,":[146],"termed":[147],"effective":[149],"total":[150],"correlation,":[151],"which":[152],"bounded":[154],"$d":[156],"\\log":[157],"S$":[158],"but":[159],"can":[160],"be":[161],"sublinear":[162,186],"or":[163,182,208],"even":[164],"constant":[165],"structured":[167],"data.":[168],"As":[169],"consequence,":[171],"provably":[174],"adapts":[175],"to":[176],"low-dimensional":[177],"structure":[178],"without":[179],"prior":[180],"knowledge":[181],"modification,":[184],"yielding":[185],"rates":[188],"various":[190],"practical":[191],"examples":[192],"(such":[193],"as":[194],"hidden":[195],"models,":[197],"image":[198],"data,":[199],"random":[201],"graphs).":[202],"Our":[203],"analysis":[204],"requires":[205],"no":[206],"boundedness":[207],"smoothness":[209],"assumptions":[210],"score":[213,219],"estimator":[214],"beyond":[215],"control":[216],"entropy":[220],"loss.":[221]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-18T00:00:00"}