{"id":"https://openalex.org/W7220671190","doi":"https://doi.org/10.48550/arxiv.2610.05297","title":"Do Neural Networks Learn Structure-Preserving Maps? A Case Study in Latent-to-Hilbert Embeddings","display_name":"Do Neural Networks Learn Structure-Preserving Maps? A Case Study in Latent-to-Hilbert Embeddings","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7220671190","doi":"https://doi.org/10.48550/arxiv.2610.05297"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.05297","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05297","pdf_url":"https://arxiv.org/pdf/2610.05297","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/2610.05297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103852204","display_name":"Muhammad Adnan Shahzad","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shahzad, Muhammad Adnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5103852204"],"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/T10320","display_name":"Neural Networks and Applications","score":0.6054999828338623,"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/T10320","display_name":"Neural Networks and Applications","score":0.6054999828338623,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.23690000176429749,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.040300000458955765,"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/structure-preserving-maps","display_name":"structure-preserving maps","score":0.9480000138282776},{"id":"https://openalex.org/keywords/angle-encoding","display_name":"angle encoding","score":0.6610000133514404},{"id":"https://openalex.org/keywords/quantum-state-encoding","display_name":"quantum state encoding","score":0.5460000038146973},{"id":"https://openalex.org/keywords/linear-regression","display_name":"linear regression","score":0.35600000619888306},{"id":"https://openalex.org/keywords/kernel-ridge-regression","display_name":"kernel ridge regression","score":0.9039999842643738},{"id":"https://openalex.org/keywords/gaussian-kernel","display_name":"Gaussian kernel","score":0.652999997138977},{"id":"https://openalex.org/keywords/singular-value-spectrum","display_name":"singular value spectrum","score":0.5839999914169312},{"id":"https://openalex.org/keywords/mnist","display_name":"MNIST","score":0.6729999780654907},{"id":"https://openalex.org/keywords/quantum-machine-learning","display_name":"quantum machine learning","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7081000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621399998664856},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4964999854564667},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4309999942779541},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.4171000123023987},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.39340001344680786},{"id":"https://openalex.org/C74887250","wikidata":"https://www.wikidata.org/wiki/Q3455892","display_name":"Principal component regression","level":3,"score":0.38119998574256897},{"id":"https://openalex.org/C49766605","wikidata":"https://www.wikidata.org/wiki/Q207643","display_name":"Linear map","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C187064257","wikidata":"https://www.wikidata.org/wiki/Q3306808","display_name":"Orthogonal basis","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C98856871","wikidata":"https://www.wikidata.org/wiki/Q1588488","display_name":"Radial basis function","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C133226019","wikidata":"https://www.wikidata.org/wiki/Q209812","display_name":"Linear span","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C54940322","wikidata":"https://www.wikidata.org/wiki/Q3997740","display_name":"Orthogonal transformation","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.2563000023365021},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.05297","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05297","pdf_url":"https://arxiv.org/pdf/2610.05297","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.2610.05297","doi":"https://doi.org/10.48550/arxiv.2610.05297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.05297","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:2610.05297","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05297","pdf_url":"https://arxiv.org/pdf/2610.05297","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/W7220671190.pdf","grobid_xml":"https://content.openalex.org/works/W7220671190.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4372270457","https://openalex.org/W7124539286","https://openalex.org/W754282277","https://openalex.org/W2109142308","https://openalex.org/W2134050500","https://openalex.org/W3033203879","https://openalex.org/W206485990","https://openalex.org/W2969578213","https://openalex.org/W7133230658","https://openalex.org/W2797081606"],"abstract_inverted_index":{"We":[0],"ask":[1],"whether":[2],"a":[3,8,12,17,46,61,137,185,205],"neural":[4],"network":[5],"can":[6],"learn":[7],"structure-preserving":[9,198],"map":[10,123],"from":[11,31,71],"compressed":[13],"latent":[14,52,67],"space":[15],"to":[16,73,84,113,158],"Hilbert-space":[18],"representation.":[19],"Using":[20],"an":[21,181],"8-dimensional":[22],"autoencoder":[23],"bottleneck":[24],"on":[25],"MNIST":[26],"and":[27,143,162,207],"$n$-qubit":[28],"product-state":[29],"targets":[30],"PCA-based":[32],"angle":[33],"encoding,":[34],"we":[35],"report":[36],"four":[37],"findings.":[38],"Although":[39],"the":[40,51,54,65,74,85,102,114,154,160,167],"target":[41,76],"angles":[42,77,88],"are":[43],"generated":[44],"by":[45,60,134],"nonlinear":[47],"sigmoid":[48],"transformation":[49],"of":[50],"projections,":[53],"resulting":[55],"mapping":[56],"is":[57,98,124],"well":[58],"approximated":[59],"linear":[62,69,197],"function":[63],"over":[64],"observed":[66],"distribution:":[68],"regression":[70,83,179],"$z$":[72],"true":[75],"achieves":[78,89],"$R^{2}":[79,90],"=":[80,91],"0.98$,":[81],"while":[82,109],"MLP's":[86],"recovered":[87],"0.91$.":[92],"The":[93,122,147],"learned":[94,148],"map's":[95],"primary":[96,169],"direction":[97,130,170],"strongly":[99],"aligned":[100],"with":[101,105,118,140,153,180],"target-induced":[103],"direction,":[104,117],"cosine":[106,119],"similarity":[107,120],"$0.989$,":[108],"remaining":[110],"nearly":[111],"orthogonal":[112],"input's":[115],"principal":[116],"$0.002$.":[121],"genuinely":[125],"rank-4:":[126],"removing":[127],"any":[128],"singular":[129],"degrades":[131],"inner-product":[132],"preservation":[133],"$2.5$--$5.9\\times$":[135],"despite":[136],"singular-value":[138],"spectrum":[139],"two":[141,144],"dominant":[142],"small":[145],"values.":[146],"subspace":[149],"does":[150],"not":[151],"coincide":[152],"PCA":[155],"basis":[156],"used":[157],"construct":[159],"target,":[161],"different":[163],"random":[164],"seeds":[165],"recover":[166],"same":[168],"but":[171],"diverge":[172],"in":[173],"higher":[174],"ranks.":[175],"Finally,":[176],"kernel":[177,183,201],"ridge":[178],"RBF":[182],"outperforms":[184],"tuned":[186],"MLP":[187],"(IP":[188],"error":[189],"$0.0144$":[190],"vs.\\":[191],"$0.0197$),":[192],"suggesting":[193],"that":[194],"for":[195],"approximately":[196],"mappings,":[199],"classical":[200],"methods":[202],"may":[203],"be":[204],"simpler":[206],"more":[208],"effective":[209],"alternative.":[210]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-07T00:00:00"}