{"id":"https://openalex.org/W7133332100","doi":"https://doi.org/10.48550/arxiv.2603.00772","title":"Initialization-Aware Score-Based Diffusion Sampling","display_name":"Initialization-Aware Score-Based Diffusion Sampling","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133332100","doi":"https://doi.org/10.48550/arxiv.2603.00772"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00772","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00772","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00772","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128014595","display_name":"Tiziano Fassina","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fassina, Tiziano","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049674739","display_name":"Gabriel Lopes Cardoso","orcid":"https://orcid.org/0000-0003-2024-5753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cardoso, Gabriel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127932702","display_name":"Sylvan Le Corff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corff, Sylvan Le","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031032994","display_name":"Thomas Romary","orcid":"https://orcid.org/0000-0002-3770-3370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romary, Thomas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5128014595"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5149000287055969,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5149000287055969,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.093299999833107,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.07159999758005142,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6682000160217285},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6636999845504761},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5918999910354614},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5820000171661377},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5415999889373779},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48429998755455017},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4749000072479248},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45559999346733093},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.45489999651908875}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6682000160217285},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6636999845504761},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5918999910354614},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5415999889373779},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5410000085830688},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48429998755455017},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4749000072479248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4645000100135803},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C98385598","wikidata":"https://www.wikidata.org/wiki/Q1339385","display_name":"Empirical distribution function","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C132878287","wikidata":"https://www.wikidata.org/wiki/Q1671727","display_name":"Inverse Gaussian distribution","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C170593435","wikidata":"https://www.wikidata.org/wiki/Q4128565","display_name":"Slice sampling","level":4,"score":0.26420000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C20326153","wikidata":"https://www.wikidata.org/wiki/Q7049638","display_name":"Nonuniform sampling","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00772","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00772","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00772","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00772","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Score-based":[0],"generative":[1,124],"models":[2],"(SGMs)":[3],"aim":[4],"at":[5],"generating":[6],"samples":[7],"from":[8,30],"a":[9,18,31,35,42,57,82],"target":[10],"distribution":[11,33],"by":[12],"approximating":[13],"the":[14,68,72,89,94,103],"reverse-time":[15,90],"dynamics":[16],"of":[17,45,61,71,102],"stochastic":[19],"differential":[20],"equation.":[21],"Despite":[22],"their":[23],"strong":[24],"empirical":[25],"performance,":[26],"classical":[27],"samplers":[28,65],"initialized":[29],"Gaussian":[32],"require":[34],"long":[36],"time":[37],"horizon":[38],"noising":[39],"typically":[40],"inducing":[41],"large":[43],"number":[44],"discretization":[46,111],"steps":[47],"and":[48,110,117],"high":[49],"computational":[50],"cost.":[51],"In":[52],"this":[53,78],"work,":[54],"we":[55,80],"present":[56],"Kullback-Leibler":[58],"convergence":[59],"analysis":[60],"Variance":[62],"Exploding":[63],"diffusion":[64],"that":[66,87],"highlights":[67],"critical":[69],"role":[70],"backward":[73],"process":[74],"initialization.":[75],"Based":[76],"on":[77,114],"result,":[79],"propose":[81],"theoretically":[83],"grounded":[84],"sampling":[85,130],"strategy":[86],"learns":[88],"initialization,":[91],"directly":[92],"minimizing":[93],"initialization":[95],"error.":[96],"The":[97],"resulting":[98],"procedure":[99],"is":[100],"independent":[101],"specific":[104],"score":[105],"training":[106],"procedure,":[107],"network":[108],"architecture,":[109],"scheme.":[112],"Experiments":[113],"toy":[115],"distributions":[116],"benchmark":[118],"datasets":[119],"demonstrate":[120],"competitive":[121],"or":[122],"improved":[123],"quality":[125],"while":[126],"using":[127],"significantly":[128],"fewer":[129],"steps.":[131]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}