{"id":"https://openalex.org/W7167046162","doi":"https://doi.org/10.48550/arxiv.2607.00170","title":"Scaling Up Thermodynamic AI Models","display_name":"Scaling Up Thermodynamic AI Models","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7167046162","doi":"https://doi.org/10.48550/arxiv.2607.00170"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.00170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00170","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.00170","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060274262","display_name":"Andrew G. Moore","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Moore, Andrew G.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5060274262"],"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/T11948","display_name":"Machine Learning in Materials Science","score":0.3246000111103058,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.3246000111103058,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11804","display_name":"Quantum many-body systems","score":0.11559999734163284,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.08799999952316284,"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/ising-model","display_name":"Ising model","score":0.7646999955177307},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7032999992370605},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5533999800682068},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4627000093460083},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.44200000166893005},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.3725000023841858},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.35569998621940613}],"concepts":[{"id":"https://openalex.org/C51329190","wikidata":"https://www.wikidata.org/wiki/Q1076349","display_name":"Ising model","level":2,"score":0.7646999955177307},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7032999992370605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5699999928474426},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47699999809265137},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.396699994802475},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.352400004863739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.3125},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2996000051498413},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.00170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00170","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.00170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00170","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Thermodynamic":[0],"computing":[1,128],"devices":[2],"based":[3],"on":[4,67,79,83],"the":[5,34,140],"Ising":[6,40,68],"model":[7],"show":[8],"great":[9],"promise":[10],"for":[11,21,25,59,64,127,136],"low-power":[12],"AI":[13,145],"inference":[14,66,99,114,130],"and":[15,55,81,92,103,124,139],"edge":[16],"computing,":[17],"but":[18],"scalable":[19,54],"methods":[20],"training":[22,60],"large":[23],"models":[24,74],"such":[26],"hardware":[27,137],"remain":[28],"limited.":[29],"Prior":[30],"theory":[31,97],"shows":[32],"that":[33,113],"time-averaged":[35],"behavior":[36],"of":[37,77,142],"high-temperature":[38,143],"Gibbs-sampled":[39],"systems":[41],"can":[42],"implement":[43],"feed-forward":[44],"neural":[45],"inference.":[46],"We":[47,89],"turn":[48],"this":[49],"theoretical":[50],"correspondence":[51],"into":[52],"a":[53,95,119],"purely":[56],"backpropagation-based":[57],"algorithm":[58],"deep":[61],"convolutional":[62],"networks":[63],"thermodynamic":[65,144],"machine":[69],"hardware.":[70],"Our":[71],"image":[72],"classification":[73],"achieve":[75],"accuracies":[76],"94.9%":[78],"CIFAR-10":[80],"76.0%":[82],"CIFAR-100":[84],"under":[85],"binary":[86],"Gibbs":[87],"sampling.":[88],"then":[90],"develop":[91],"experimentally":[93],"validate":[94],"mathematical":[96],"relating":[98],"cost":[100,115],"to":[101],"accuracy":[102],"controlling":[104],"autocorrelation":[105],"times.":[106],"Subsequently,":[107],"we":[108,133],"calculate":[109],"asymptotic":[110],"results":[111],"showing":[112],"is":[116],"bounded":[117],"by":[118],"well-controlled":[120],"tradeoff":[121],"with":[122],"performance":[123],"exhibit":[125],"algorithms":[126],"optimal":[129],"schedules.":[131],"Finally,":[132],"discuss":[134],"implications":[135],"development":[138],"future":[141],"models.":[146]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-03T00:00:00"}