{"id":"https://openalex.org/W7162639839","doi":"https://doi.org/10.48550/arxiv.2605.27662","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","display_name":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162639839","doi":"https://doi.org/10.48550/arxiv.2605.27662"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27662","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.2605.27662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137261842","display_name":"Teodor-Mihai Stupariu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stupariu, Teodor-Mihai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081887157","display_name":"Andrei Manolache","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manolache, Andrei","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/T11948","display_name":"Machine Learning in Materials Science","score":0.684499979019165,"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":0.684499979019165,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.03680000081658363,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.03620000183582306,"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/equivariant-map","display_name":"Equivariant map","score":0.8769000172615051},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6736999750137329},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.6111000180244446},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4681999981403351},{"id":"https://openalex.org/keywords/homogeneous-space","display_name":"Homogeneous space","score":0.4496999979019165},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.44690001010894775},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3776000142097473}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.8769000172615051},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6736999750137329},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4194999933242798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39879998564720154},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3776000142097473},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C205334942","wikidata":"https://www.wikidata.org/wiki/Q3151","display_name":"Muon","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27662","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.2605.27662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27662","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":[{"score":0.57110995054245,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Equivariant":[0],"neural":[1],"networks":[2],"encode":[3],"geometric":[4,60,143],"symmetries":[5],"by":[6,51,109],"construction,":[7],"yet":[8],"they":[9],"are":[10],"often":[11],"difficult":[12],"to":[13],"optimize":[14],"and":[15,54,59,64,97,103,121,125,130,142],"can":[16],"underperform":[17],"less":[18],"constrained":[19],"architectures.":[20],"A":[21],"growing":[22],"body":[23],"of":[24,41,100],"work":[25],"addresses":[26],"this":[27,49],"through":[28,91],"architectural":[29],"modifications":[30],"such":[31],"as":[32],"constraint":[33],"relaxation":[34],"or":[35],"approximate":[36],"equivariance,":[37],"while":[38],"the":[39,42,71,87,137,150],"role":[40],"optimizer":[43,140],"remains":[44],"comparatively":[45],"underexplored.":[46],"We":[47,84],"study":[48],"direction":[50],"comparing":[52],"Muon":[53,75,110],"Adam":[55,79],"across":[56,80],"several":[57],"equivariant":[58],"architectures":[61,82],"under":[62],"pointcloud":[63],"molecular":[65],"learning":[66],"settings.":[67],"On":[68],"ModelNet40,":[69],"where":[70],"comparison":[72],"is":[73],"clearest,":[74],"consistently":[76],"improves":[77],"over":[78],"all":[81],"considered.":[83],"then":[85],"analyze":[86],"trained":[88],"ModelNet40":[89],"checkpoints":[90,107],"Hessian":[92,113],"estimates,":[93],"loss":[94,119],"surface":[95],"visualizations,":[96],"spectral":[98],"properties":[99],"learned":[101,123],"weights":[102,124],"intermediate":[104],"representations.":[105],"The":[106],"reached":[108],"have":[111,127],"larger":[112],"curvature":[114],"summaries":[115],"but":[116],"more":[117],"regular":[118],"surfaces,":[120],"their":[122],"representations":[126],"higher":[128],"stable":[129],"effective":[131],"ranks.":[132],"These":[133],"observations":[134],"suggest":[135],"that":[136],"interaction":[138],"between":[139],"design":[141],"inductive":[144],"bias":[145],"deserves":[146],"further":[147],"attention":[148],"from":[149],"community.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}