{"id":"https://openalex.org/W7224869095","doi":"https://doi.org/10.48550/arxiv.2610.40485","title":"The Precision Wall: An Optimizer-Dependent Boundary for Optimization under Power-Law Measurement Spectra","display_name":"The Precision Wall: An Optimizer-Dependent Boundary for Optimization under Power-Law Measurement Spectra","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224869095","doi":"https://doi.org/10.48550/arxiv.2610.40485"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.40485","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40485","pdf_url":"https://arxiv.org/pdf/2610.40485","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.40485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160238382","display_name":"Lngel Kyo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kyo, Lngel","raw_affiliation_strings":["A2O Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A2O Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160238382"],"corresponding_institution_ids":[],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6488999724388123,"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":0.6488999724388123,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.329800009727478,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-local-minima","display_name":"spurious local minima","score":0.8320000171661377},{"id":"https://openalex.org/keywords/hessian-eigenvalues","display_name":"Hessian eigenvalues","score":0.6140000224113464},{"id":"https://openalex.org/keywords/numerical-precision","display_name":"numerical precision","score":0.4790000021457672},{"id":"https://openalex.org/keywords/adam-optimizer","display_name":"Adam optimizer","score":0.8450000286102295},{"id":"https://openalex.org/keywords/first-order-methods","display_name":"first-order methods","score":0.5210000276565552},{"id":"https://openalex.org/keywords/critical-exponents","display_name":"critical exponents","score":0.3919999897480011}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6557000279426575},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.6344000101089478},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.5238000154495239},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5170000195503235},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42160001397132874},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3889999985694885},{"id":"https://openalex.org/C152822103","wikidata":"https://www.wikidata.org/wiki/Q7575207","display_name":"Spectral shape analysis","level":3,"score":0.3887999951839447},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C184389593","wikidata":"https://www.wikidata.org/wiki/Q603159","display_name":"Curve fitting","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C2781212128","wikidata":"https://www.wikidata.org/wiki/Q2256181","display_name":"Duct (anatomy)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.40485","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40485","pdf_url":"https://arxiv.org/pdf/2610.40485","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.2610.40485","doi":"https://doi.org/10.48550/arxiv.2610.40485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.40485","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.40485","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40485","pdf_url":"https://arxiv.org/pdf/2610.40485","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224869095.pdf","grobid_xml":"https://content.openalex.org/works/W7224869095.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3132617758","https://openalex.org/W4281484845","https://openalex.org/W7221771607","https://openalex.org/W3081383800","https://openalex.org/W7214914749","https://openalex.org/W3037839452","https://openalex.org/W7208721042","https://openalex.org/W3128056260","https://openalex.org/W7130857613","https://openalex.org/W4387355977"],"abstract_inverted_index":{"In":[0],"low-rank":[1],"matrix":[2],"sensing":[3],"of":[4,28,77,124],"a":[5,38,47,101,125,155,166],"rank-$D$":[6],"factor":[7],"$U^\\ast":[8],"\\in":[9,129,133],"\\mathbb{R}^{V":[10],"\\times":[11,131],"D}$,":[12],"replacing":[13],"isotropic":[14],"Gaussian":[15],"designs":[16],"with":[17],"power-law":[18],"measurement":[19],"covariance":[20],"$\u03a3=":[21],"\\mathrm{diag}(j^{-s})_{j=1}^V$":[22],"leaves":[23],"the":[24,52,55,72,86],"Burer--Monteiro":[25],"landscape":[26],"free":[27],"spurious":[29],"local":[30],"minima,":[31],"yet":[32],"division-normalised":[33],"first-order":[34],"optimizers":[35],"stall":[36],"above":[37],"critical":[39],"exponent":[40],"$s^\\ast$.":[41],"We":[42],"trace":[43],"this":[44,68,113],"failure":[45],"to":[46],"numerical":[48],"precision":[49],"wall.":[50],"At":[51],"ground":[53],"truth,":[54],"smallest":[56],"non-gauge":[57],"expected":[58],"Hessian":[59],"eigenvalue":[60],"scales":[61],"at":[62,150,165],"leading":[63],"order":[64],"as":[65],"$V^{-(s+1)}D^{-s}$.":[66],"When":[67],"curvature":[69],"drops":[70],"below":[71,161],"effective":[73],"denominator":[74],"floor":[75],"$\u03b5_O$":[76],"optimizer":[78],"$O$,":[79],"normalisation":[80],"noise":[81],"overwhelms":[82],"rare-direction":[83],"gradients,":[84],"yielding":[85],"leading-order":[87],"boundary":[88],"$s^\\ast_O(V,":[89],"D)":[90],"=":[91,152,163],"[\\log(1/\u03b5_O)":[92],"-":[93],"\\log":[94],"V]/\\log(VD)":[95],"+":[96],"\u03b4_O$,":[97],"where":[98],"$\u03b4_O$":[99],"is":[100],"metric-dependent":[102],"detection":[103],"lag.":[104],"With":[105],"$\u03b4_{\\mathrm{Adam}}$":[106],"calibrated":[107],"on":[108],"four":[109],"configurations":[110],"and":[111,138,144,159],"frozen,":[112],"formula":[114],"predicts":[115],"Adam's":[116],"onset":[117],"within":[118],"$0.45$":[119],"across":[120],"all":[121],"16":[122],"cells":[123],"held-out":[126],"grid":[127],"($V":[128],"\\{64,128,256,512\\}":[130],"D":[132],"\\{4,8,16,32\\}$),":[134],"separates":[135],"fixed-$VD$":[136],"pairs,":[137],"distinguishes":[139],"denominator-precision":[140],"walls":[141],"from":[142],"conditioning":[143],"sign-quantisation":[145],"walls.":[146],"The":[147],"approximation":[148],"fails":[149],"$D":[151],"2$,":[153],"reflects":[154],"finite-$D$":[156],"spectral":[157],"crossover,":[158],"saturates":[160],"$\\varepsilon_0":[162],"10^{-8}$":[164],"dynamical":[167],"floor.":[168]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}