{"id":"https://openalex.org/W7161296787","doi":"https://doi.org/10.48550/arxiv.2605.14659","title":"Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning","display_name":"Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161296787","doi":"https://doi.org/10.48550/arxiv.2605.14659"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14659","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.2605.14659","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136273597","display_name":"Shin So","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"So, Shin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136255545","display_name":"Kyelim Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Kyelim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049196468","display_name":"Albert No","orcid":"https://orcid.org/0000-0002-6346-4182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"No, Albert","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.555899977684021,"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":0.555899977684021,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.10209999978542328,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10320","display_name":"Neural Networks and Applications","score":0.04410000145435333,"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/generalization","display_name":"Generalization","score":0.5164999961853027},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4810999929904938},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4189999997615814},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.37929999828338623},{"id":"https://openalex.org/keywords/probably-approximately-correct-learning","display_name":"Probably approximately correct learning","score":0.3107999861240387},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.29919999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541700005531311},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.3107999861240387},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14659","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.2605.14659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14659","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":{"Critical-data-size":[0],"accounts":[1],"of":[2,125],"grokking":[3],"suggest":[4],"a":[5,33],"natural":[6],"post-threshold":[7,113],"intuition:":[8],"once":[9],"training":[10,92],"data":[11,20,120],"is":[12],"sufficient":[13],"to":[14,89],"identify":[15,136],"the":[16,57,75,111,118,123,128,141],"underlying":[17],"rule,":[18],"additional":[19],"should":[21],"accelerate":[22,100],"validation":[23,46,79],"convergence.":[24],"We":[25],"show":[26,110],"that":[27,95,131],"this":[28,61],"intuition":[29],"can":[30,85,99,146],"fail":[31],"in":[32,74],"controlled":[34],"structured-output":[35,137],"task.":[36],"In":[37],"Needleman--Wunsch":[38],"(NW)":[39],"matrix":[40],"generation,":[41],"small":[42],"Transformers":[43],"reach":[44,90],"high":[45,91],"exact-match":[47],"accuracy":[48],"fastest":[49],"at":[50,56],"an":[51],"intermediate":[52],"dataset":[53,129],"size,":[54],"not":[55,109],"largest":[58],"one.":[59],"Past":[60],"dataset-size":[62],"sweet":[63],"spot,":[64],"generalization":[65,126],"remains":[66],"achievable":[67],"but":[68],"requires":[69],"more":[70],"gradient":[71],"updates.":[72],"Conversely,":[73],"regime":[76],"where":[77,139],"partial":[78],"competence":[80],"first":[81],"appears,":[82],"larger":[83],"datasets":[84],"require":[86],"fewer":[87],"updates":[88],"accuracy,":[93],"suggesting":[94],"emerging":[96],"rule":[97,142],"structure":[98],"fitting":[101],"beyond":[102],"example-wise":[103],"memorization.":[104],"A":[105],"multiplication":[106],"baseline":[107],"does":[108],"same":[112],"slowdown.":[114],"These":[115],"results":[116],"separate":[117],"critical":[119],"size":[121,130],"for":[122],"onset":[124],"from":[127],"optimizes":[132],"update-based":[133],"convergence,":[134],"and":[135,143],"tasks":[138],"learning":[140],"completing":[144],"exact-fitting":[145],"diverge.":[147]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-16T00:00:00"}