{"id":"https://openalex.org/W7214746384","doi":"https://doi.org/10.48550/arxiv.2609.32279","title":"SIMANF: Sample Free Learning of Unnormalized Distributions via Simulated Annealing in Normalizing Flows","display_name":"SIMANF: Sample Free Learning of Unnormalized Distributions via Simulated Annealing in Normalizing Flows","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214746384","doi":"https://doi.org/10.48550/arxiv.2609.32279"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32279","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32279","pdf_url":"https://arxiv.org/pdf/2609.32279","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/2609.32279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107840108","display_name":"Vikas Kanaujia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164565","display_name":"Mahindra University","ror":"https://ror.org/05751b994","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210164565"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Kanaujia, Vikas","raw_affiliation_strings":["Mahindra University Department of Electrical and Computer Engineering Hyderabad , Telangana , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mahindra University Department of Electrical and Computer Engineering Hyderabad , Telangana , India","institution_ids":["https://openalex.org/I4210164565"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5107840108"],"corresponding_institution_ids":["https://openalex.org/I4210164565"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.7705000042915344,"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":0.7705000042915344,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.14429999887943268,"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":0.03460000082850456,"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/normalizing-flows","display_name":"normalizing flows","score":0.9610000252723694},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"simulated annealing","score":1.0},{"id":"https://openalex.org/keywords/mode-collapse","display_name":"mode collapse","score":0.7820000052452087},{"id":"https://openalex.org/keywords/reverse-kl-divergence","display_name":"reverse KL divergence","score":0.8199999928474426},{"id":"https://openalex.org/keywords/importance-weighting","display_name":"importance weighting","score":0.6610000133514404},{"id":"https://openalex.org/keywords/multimodal-distributions","display_name":"multimodal distributions","score":0.7639999985694885},{"id":"https://openalex.org/keywords/high-dimensional-sampling","display_name":"high-dimensional sampling","score":0.5249999761581421}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5752000212669373},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5429999828338623},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41620001196861267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39730000495910645},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.34389999508857727},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32279","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32279","pdf_url":"https://arxiv.org/pdf/2609.32279","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.2609.32279","doi":"https://doi.org/10.48550/arxiv.2609.32279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32279","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:2609.32279","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32279","pdf_url":"https://arxiv.org/pdf/2609.32279","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214746384.pdf","grobid_xml":"https://content.openalex.org/works/W7214746384.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403816308","https://openalex.org/W4290064682","https://openalex.org/W4417325998","https://openalex.org/W7160375615","https://openalex.org/W6958057370","https://openalex.org/W4407359505","https://openalex.org/W7214768920","https://openalex.org/W3012661842","https://openalex.org/W4402825276","https://openalex.org/W3216975124"],"abstract_inverted_index":{"Efficiently":[0],"learning":[1],"and":[2,72,132,145],"sampling":[3],"from":[4,39,62],"high":[5,146],"dimensional,":[6],"multimodal":[7],"unnormalized":[8,34,136],"distributions":[9,144],"without":[10],"target":[11,35,60,70,99,128],"samples":[12,22,120,129],"remains":[13],"a":[14,45,63,103],"challenging":[15],"problem.":[16],"Although":[17],"normalizing":[18,54],"flows":[19],"can":[20],"generate":[21],"efficiently,":[23],"training":[24,131],"based":[25],"on":[26,142],"the":[27,33,59,68,74,82,87,98,108,123,135],"reverse":[28,109],"KL":[29,110,117],"divergence":[30,111],"using":[31,119],"only":[32,134],"density":[36],"may":[37],"suffer":[38],"mode":[40,90],"collapse.":[41],"We":[42,138],"introduce":[43],"SIMANF,":[44],"sample":[46],"free":[47],"framework":[48],"that":[49],"integrates":[50],"simulated":[51],"annealing":[52],"with":[53,112],"flows.":[55],"SIMANF":[56,125],"progressively":[57,93],"transforms":[58],"distribution":[61,71],"smooth":[64],"initial":[65],"form":[66],"to":[67],"original":[69],"trains":[73],"flow":[75],"sequentially":[76],"across":[77],"these":[78],"stages.":[79],"By":[80],"transferring":[81],"learned":[83],"representation":[84],"between":[85],"stages,":[86],"method":[88],"promotes":[89],"coverage":[91],"while":[92],"capturing":[94],"finer":[95],"features":[96],"of":[97],"distribution.":[100,153],"Following":[101],"annealing,":[102],"final":[104],"refinement":[105],"stage":[106],"combines":[107],"an":[113],"importance":[114],"weighted":[115],"forward":[116],"objective":[118],"generated":[121],"by":[122],"flow.":[124],"requires":[126],"no":[127],"during":[130],"uses":[133],"density.":[137],"demonstrate":[139],"its":[140],"effectiveness":[141],"Many-Well":[143],"dimensional":[147],"Scalar":[148],"Phi4":[149],"lattice":[150],"field":[151],"theory":[152]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-30T00:00:00"}