{"id":"https://openalex.org/W4417049650","doi":"https://doi.org/10.48550/arxiv.2510.02730","title":"Dale meets Langevin: A Multiplicative Denoising Diffusion Model","display_name":"Dale meets Langevin: A Multiplicative Denoising Diffusion Model","publication_year":2025,"publication_date":"2025-10-03","ids":{"openalex":"https://openalex.org/W4417049650","doi":"https://doi.org/10.48550/arxiv.2510.02730"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.02730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.02730","pdf_url":"https://arxiv.org/pdf/2510.02730","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.02730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111148977","display_name":"Nishanth Shetty","orcid":"https://orcid.org/0009-0001-0158-4656"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shetty, Nishanth","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120714997","display_name":"Madhava Prasath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasath, Madhava","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005652970","display_name":"Chandra Sekhar Seelamantula","orcid":"https://orcid.org/0000-0001-9049-1912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seelamantula, Chandra Sekhar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111148977"],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6715999841690063,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6715999841690063,"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/T10581","display_name":"Neural dynamics and brain function","score":0.046799998730421066,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03669999912381172,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6779000163078308},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.5976999998092651},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5649999976158142},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5131000280380249},{"id":"https://openalex.org/keywords/multiplicative-noise","display_name":"Multiplicative noise","score":0.49639999866485596},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.45649999380111694},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43230000138282776},{"id":"https://openalex.org/keywords/descent-direction","display_name":"Descent direction","score":0.3977999985218048},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3765000104904175}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6779000163078308},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.5976999998092651},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5649999976158142},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5117999911308289},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.49639999866485596},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.47850000858306885},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43230000138282776},{"id":"https://openalex.org/C116149140","wikidata":"https://www.wikidata.org/wiki/Q2070951","display_name":"Descent direction","level":4,"score":0.3977999985218048},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38440001010894775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37389999628067017},{"id":"https://openalex.org/C112401455","wikidata":"https://www.wikidata.org/wiki/Q178036","display_name":"Brownian motion","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35100001096725464},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.02730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.02730","pdf_url":"https://arxiv.org/pdf/2510.02730","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2510.02730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.02730","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.02730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.02730","pdf_url":"https://arxiv.org/pdf/2510.02730","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Gradient":[0],"descent":[1,30,81,150],"has":[2,42],"proven":[3],"to":[4,85,99,189],"be":[5,190],"a":[6,135,159,191,207,217,248],"powerful":[7],"and":[8,65,126,182,204,226],"effective":[9],"technique":[10],"for":[11,47,162,173,196,201,212],"optimization":[12,31,82],"in":[13,20,27,38,206],"numerous":[14],"machine":[15],"learning":[16,26,37,51],"applications.":[17],"Recent":[18],"advances":[19],"computational":[21],"neuroscience":[22],"have":[23],"shown":[24],"that":[25,63,93,128],"standard":[28],"gradient":[29,80,149],"formulation":[32],"is":[33,56,110,180,243],"not":[34,69],"consistent":[35],"with":[36,105,119,142],"biological":[39],"systems.":[40],"This":[41,194],"opened":[43],"up":[44],"interesting":[45],"avenues":[46],"building":[48],"biologically":[49,249],"inspired":[50,57,250],"techniques.":[52],"One":[53],"such":[54],"approach":[55],"by":[58,171],"Dale's":[59,154],"law,":[60],"which":[61,139],"states":[62],"inhibitory":[64],"excitatory":[66],"synapses":[67],"do":[68],"swap":[70],"roles":[71],"during":[72],"the":[73,91,95,100,111,120,130,143,147,167,183,233,237,244],"course":[74],"of":[75,146,198,232,239,247],"learning.":[76],"The":[77],"resulting":[78],"exponential":[79,148],"scheme":[83,211],"leads":[84],"log-normally":[86,177],"distributed":[87,178],"synaptic":[88],"weights.":[89],"Interestingly,":[90],"density":[92],"satisfies":[94],"Fokker-Planck":[96],"equation":[97,103],"corresponding":[98,131],"stochastic":[101],"differential":[102],"(SDE)":[104],"geometric":[106,123,258],"Brownian":[107,124,259],"motion":[108],"(GBM)":[109],"log-normal":[112,218],"density.":[113,219],"Leveraging":[114],"this":[115,242],"connection,":[116],"we":[117,157],"start":[118],"SDE":[121,133],"governing":[122],"motion,":[125],"show":[127],"discretizing":[129],"reverse-time":[132],"yields":[134],"multiplicative":[136,163,209,254],"update":[137,151,210],"rule,":[138],"surprisingly,":[140],"coincides":[141],"sampling":[144],"equivalent":[145],"founded":[152,256],"on":[153,222,257],"law.":[155],"Furthermore,":[156],"propose":[158],"new":[160,234],"formalism":[161,186],"denoising":[164],"score-matching,":[165],"subsuming":[166],"loss":[168],"function":[169],"proposed":[170,184],"Hyvaerinen":[172],"non-negative":[174],"data.":[175],"Indeed,":[176],"data":[179,203],"positive":[181],"score-matching":[185],"turns":[187],"out":[188],"natural":[192],"fit.":[193],"allows":[195],"training":[197],"score-based":[199],"models":[200],"image":[202],"results":[205,221],"novel":[208],"sample":[213],"generation":[214],"starting":[215],"from":[216],"Experimental":[220],"MNIST,":[223,225],"Fashion":[224],"Kuzushiji":[227],"datasets":[228],"demonstrate":[229],"generative":[230,251],"capability":[231],"scheme.":[235],"To":[236],"best":[238],"our":[240],"knowledge,":[241],"first":[245],"instance":[246],"model":[252],"employing":[253],"updates,":[255],"motion.":[260]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}