{"id":"https://openalex.org/W7140163830","doi":"https://doi.org/10.48550/arxiv.2603.20631","title":"LassoFlexNet: Flexible Neural Architecture for Tabular Data","display_name":"LassoFlexNet: Flexible Neural Architecture for Tabular Data","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7140163830","doi":"https://doi.org/10.48550/arxiv.2603.20631"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20631","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.20631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013213677","display_name":"Kry Yik Chau Lui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lui, Kry Yik Chau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146706683","display_name":"Cheng Chi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018003007","display_name":"K. Basu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Basu, Kishore","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112457697","display_name":"Yanshuai Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yanshuai","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.18240000307559967,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.18240000307559967,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.17319999635219574,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12250000238418579,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robustness","display_name":"Robustness (evolution)","score":0.65420001745224},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5307999849319458},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.527899980545044},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4327999949455261},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3869999945163727},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.3490999937057495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34689998626708984},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.32519999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559000015258789},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.65420001745224},{"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/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5307999849319458},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20631","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.20631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20631","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"their":[1],"dominance":[2],"in":[3],"vision":[4],"and":[5,42,54,64,136,144],"language,":[6],"deep":[7,30],"neural":[8],"networks":[9],"often":[10],"underperform":[11],"relative":[12,122],"to":[13,33,100,119],"tree-based":[14,115],"models":[15],"on":[16],"tabular":[17],"data.":[18],"To":[19],"bridge":[20],"this":[21],"gap,":[22],"we":[23,86],"incorporate":[24],"five":[25],"key":[26],"inductive":[27],"biases":[28],"into":[29],"learning:":[31],"robustness":[32],"irrelevant":[34],"features,":[35],"axis":[36],"alignment,":[37],"localized":[38],"irregularities,":[39],"feature":[40],"heterogeneity,":[41],"training":[43],"stability.":[44],"We":[45,128],"propose":[46],"\\emph{LassoFlexNet},":[47],"an":[48],"architecture":[49],"that":[50,81],"evaluates":[51],"the":[52,140],"linear":[53],"nonlinear":[55],"marginal":[56],"contribution":[57],"of":[58,147],"each":[59],"input":[60],"via":[61],"Per-Feature":[62],"Embeddings,":[63],"sparsely":[65],"selects":[66],"relevant":[67],"variables":[68],"using":[69],"a":[70,88,120],"Tied":[71],"Group":[72],"Lasso":[73],"mechanism.":[74],"Because":[75],"these":[76,130],"components":[77],"introduce":[78],"optimization":[79],"challenges":[80],"destabilize":[82],"standard":[83],"proximal":[84],"methods,":[85],"develop":[87],"\\emph{Sequential":[89],"Hierarchical":[90],"Proximal":[91],"Adaptive":[92],"Gradient":[93],"optimizer":[94],"with":[95,133],"exponential":[96],"moving":[97],"averages":[98],"(EMA)}":[99],"ensure":[101],"stable":[102],"convergence.":[103],"Across":[104],"$52$":[105],"datasets":[106],"from":[107],"three":[108],"benchmarks,":[109],"LassoFlexNet":[110],"matches":[111],"or":[112],"outperforms":[113],"leading":[114],"models,":[116],"achieving":[117],"up":[118],"$10$\\%":[121],"gain,":[123],"while":[124],"maintaining":[125],"Lasso-like":[126],"interpretability.":[127],"substantiate":[129],"empirical":[131],"results":[132],"ablation":[134],"studies":[135],"theoretical":[137],"proofs":[138],"confirming":[139],"architecture's":[141],"enhanced":[142],"expressivity":[143],"structural":[145],"breaking":[146],"undesired":[148],"rotational":[149],"invariance.":[150]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-03-25T00:00:00"}