{"id":"https://openalex.org/W7160377730","doi":"https://doi.org/10.48550/arxiv.2605.03718","title":"Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2","display_name":"Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160377730","doi":"https://doi.org/10.48550/arxiv.2605.03718"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.03718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03718","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.03718","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135451064","display_name":"Ewan Davies","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davies, Ewan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135471160","display_name":"Holden Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Holden","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020732123","display_name":"Juspreet Singh Sandhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandhu, Juspreet Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114096896","display_name":"Jonathan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Jonathan","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":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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.5633000135421753,"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":0.5633000135421753,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.1615999937057495,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.043800000101327896,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.784600019454956},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.5546000003814697},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.45320001244544983},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4090000092983246},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.39399999380111694},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.3779999911785126},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.35749998688697815},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.34940001368522644},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.34380000829696655}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.784600019454956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7407000064849854},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.5546000003814697},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5091000199317932},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48489999771118164},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41920000314712524},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4090000092983246},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C21031990","wikidata":"https://www.wikidata.org/wiki/Q355020","display_name":"Probability measure","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C73729460","wikidata":"https://www.wikidata.org/wiki/Q17023339","display_name":"Hessian equation","level":4,"score":0.29809999465942383},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C104824951","wikidata":"https://www.wikidata.org/wiki/Q830124","display_name":"Girsanov theorem","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2777630202","wikidata":"https://www.wikidata.org/wiki/Q5527840","display_name":"Gaussian measure","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.03718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03718","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":"doi:10.48550/arxiv.2605.03718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03718","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":"Preprint"},"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":{"We":[0,150],"give":[1],"a":[2,69,103,132,177],"polynomial-time":[3],"algorithm":[4,71],"to":[5,22,35,145,167,171,176,182],"sample":[6],"from":[7],"the":[8,12,41,57,82,85,117,127,137,141,163,169,184,187],"Gibbs":[9,87],"measure":[10],"of":[11,84,123,140],"Sherrington-Kirkpatrick":[13],"model":[14],"with":[15,126,155,159,186],"negligible":[16],"total-variation":[17],"distance":[18],"(TVD)":[19],"error":[20,31,110,170],"up":[21,34,175],"inverse":[23],"temperature":[24],"$\u03b2<":[25,45],"1/2$.":[26],"Prior":[27],"work":[28],"obtained":[29],"TVD":[30,174],"guarantees":[32,48],"only":[33,49],"$\u03b2\\approx":[36],"0.295$,":[37],"while":[38],"results":[39],"covering":[40],"entire":[42],"replica-symmetric":[43],"regime":[44],"1$":[46],"gave":[47],"in":[50,147,173],"Wasserstein":[51,109],"distance.":[52],"Our":[53],"approach":[54],"demonstrates":[55],"that":[56,102],"same":[58],"potential":[59],"Hessian":[60,128,142],"ascent":[61,129],"previously":[62],"developed":[63],"for":[64,112],"optimization":[65],"also":[66],"functions":[67],"as":[68],"sampling":[70,185],"by":[72,92],"implementing":[73],"algorithmic":[74],"stochastic":[75,124],"localization":[76,125],"at":[77],"high":[78],"temperature.":[79],"By":[80],"estimating":[81],"covariance":[83],"tilted":[86],"distribution":[88],"via":[89],"Gaussian":[90],"integration":[91],"parts,":[93],"overlap":[94],"concentration,":[95],"and":[96,131,181],"precise":[97],"cavity":[98],"estimates,":[99],"we":[100],"show":[101],"Hessian-ascent":[104],"process":[105,130],"achieves":[106],"an":[107],"$O(1)$":[108,146],"guarantee":[111],"finite-time":[113],"localization,":[114],"improving":[115],"on":[116,162],"previous":[118],"$o(n)$.":[119],"A":[120],"careful":[121],"comparison":[122],"free":[133],"probability":[134],"argument":[135],"controlling":[136],"diagonal":[138],"sub-algebra":[139],"improves":[143],"this":[144],"KL":[148],"divergence.":[149],"then":[151],"use":[152],"Jarzynski's":[153],"equality":[154],"rejection":[156],"sampling,":[157],"along":[158],"entropy":[160],"contraction":[161],"time-$T$":[164],"localized":[165],"distribution,":[166],"refine":[168],"$o(1)$":[172],"constant":[178],"time":[179],"$T$":[180],"complete":[183],"polarized":[188],"walk.":[189]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-07T00:00:00"}