Generalized Kernel Regularized Least Squares

Kernel Regularized Least Squares (KRLS) is a popular method for flexibly estimating models that may have complex relationships between variables. However, its usefulness to many researchers is limited for two reasons. First, existing approaches are inflexible and do not allow KRLS to be combined wit...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-09
Hauptverfasser: Chang, Qing, Goplerud, Max
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Chang, Qing
Goplerud, Max
description Kernel Regularized Least Squares (KRLS) is a popular method for flexibly estimating models that may have complex relationships between variables. However, its usefulness to many researchers is limited for two reasons. First, existing approaches are inflexible and do not allow KRLS to be combined with theoretically-motivated extensions such as random effects, unregularized fixed effects, or non-Gaussian outcomes. Second, estimation is extremely computationally intensive for even modestly sized datasets. Our paper addresses both concerns by introducing generalized KRLS (gKRLS). We note that KRLS can be re-formulated as a hierarchical model thereby allowing easy inference and modular model construction where KRLS can be used alongside random effects, splines, and unregularized fixed effects. Computationally, we also implement random sketching to dramatically accelerate estimation while incurring a limited penalty in estimation quality. We demonstrate that gKRLS can be fit on datasets with tens of thousands of observations in under one minute. Further, state-of-the-art techniques that require fitting the model over a dozen times (e.g. meta-learners) can be estimated quickly.
doi_str_mv 10.48550/arxiv.2209.14355
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2209_14355</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2719593866</sourcerecordid><originalsourceid>FETCH-LOGICAL-a955-3f0649758fac2cfcc3b120f5aa4d17ba54247c311a652f415b2428ad370ab6323</originalsourceid><addsrcrecordid>eNotj1FLwzAUhYMgOOZ-gE8WfLUzuTc3aR9l6CYWBN17uW0T6ajdlqyi_npn59OBw8fhfEJcKTnXGZG84_DVfs4BZD5XGonOxAQQVZppgAsxi3EjpQRjgQgn4nbpehe4a39ckzy70LsueXXvQ8dhrArH8ZC87QcOLl6Kc89ddLP_nIr148N6sUqLl-XT4r5IOSdK0Uujc0uZ5xpqX9dYKZCemHWjbMWkQdsalWJD4LWiCjRk3KCVXBkEnIrr0-yoUu5C-8Hhu_xTKkelI3FzInZhux9cPJSb7RD646cSrMopx8wY_AU_hUz4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2719593866</pqid></control><display><type>article</type><title>Generalized Kernel Regularized Least Squares</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Chang, Qing ; Goplerud, Max</creator><creatorcontrib>Chang, Qing ; Goplerud, Max</creatorcontrib><description>Kernel Regularized Least Squares (KRLS) is a popular method for flexibly estimating models that may have complex relationships between variables. However, its usefulness to many researchers is limited for two reasons. First, existing approaches are inflexible and do not allow KRLS to be combined with theoretically-motivated extensions such as random effects, unregularized fixed effects, or non-Gaussian outcomes. Second, estimation is extremely computationally intensive for even modestly sized datasets. Our paper addresses both concerns by introducing generalized KRLS (gKRLS). We note that KRLS can be re-formulated as a hierarchical model thereby allowing easy inference and modular model construction where KRLS can be used alongside random effects, splines, and unregularized fixed effects. Computationally, we also implement random sketching to dramatically accelerate estimation while incurring a limited penalty in estimation quality. We demonstrate that gKRLS can be fit on datasets with tens of thousands of observations in under one minute. Further, state-of-the-art techniques that require fitting the model over a dozen times (e.g. meta-learners) can be estimated quickly.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2209.14355</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Complex variables ; Computer Science - Learning ; Datasets ; Estimation ; Kernels ; Least squares ; Modular construction ; Statistics - Applications ; Statistics - Machine Learning</subject><ispartof>arXiv.org, 2023-09</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2209.14355$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1017/pan.2023.27$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Chang, Qing</creatorcontrib><creatorcontrib>Goplerud, Max</creatorcontrib><title>Generalized Kernel Regularized Least Squares</title><title>arXiv.org</title><description>Kernel Regularized Least Squares (KRLS) is a popular method for flexibly estimating models that may have complex relationships between variables. However, its usefulness to many researchers is limited for two reasons. First, existing approaches are inflexible and do not allow KRLS to be combined with theoretically-motivated extensions such as random effects, unregularized fixed effects, or non-Gaussian outcomes. Second, estimation is extremely computationally intensive for even modestly sized datasets. Our paper addresses both concerns by introducing generalized KRLS (gKRLS). We note that KRLS can be re-formulated as a hierarchical model thereby allowing easy inference and modular model construction where KRLS can be used alongside random effects, splines, and unregularized fixed effects. Computationally, we also implement random sketching to dramatically accelerate estimation while incurring a limited penalty in estimation quality. We demonstrate that gKRLS can be fit on datasets with tens of thousands of observations in under one minute. Further, state-of-the-art techniques that require fitting the model over a dozen times (e.g. meta-learners) can be estimated quickly.</description><subject>Complex variables</subject><subject>Computer Science - Learning</subject><subject>Datasets</subject><subject>Estimation</subject><subject>Kernels</subject><subject>Least squares</subject><subject>Modular construction</subject><subject>Statistics - Applications</subject><subject>Statistics - Machine Learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotj1FLwzAUhYMgOOZ-gE8WfLUzuTc3aR9l6CYWBN17uW0T6ajdlqyi_npn59OBw8fhfEJcKTnXGZG84_DVfs4BZD5XGonOxAQQVZppgAsxi3EjpQRjgQgn4nbpehe4a39ckzy70LsueXXvQ8dhrArH8ZC87QcOLl6Kc89ddLP_nIr148N6sUqLl-XT4r5IOSdK0Uujc0uZ5xpqX9dYKZCemHWjbMWkQdsalWJD4LWiCjRk3KCVXBkEnIrr0-yoUu5C-8Hhu_xTKkelI3FzInZhux9cPJSb7RD646cSrMopx8wY_AU_hUz4</recordid><startdate>20230908</startdate><enddate>20230908</enddate><creator>Chang, Qing</creator><creator>Goplerud, Max</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20230908</creationdate><title>Generalized Kernel Regularized Least Squares</title><author>Chang, Qing ; Goplerud, Max</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a955-3f0649758fac2cfcc3b120f5aa4d17ba54247c311a652f415b2428ad370ab6323</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Complex variables</topic><topic>Computer Science - Learning</topic><topic>Datasets</topic><topic>Estimation</topic><topic>Kernels</topic><topic>Least squares</topic><topic>Modular construction</topic><topic>Statistics - Applications</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Chang, Qing</creatorcontrib><creatorcontrib>Goplerud, Max</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chang, Qing</au><au>Goplerud, Max</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Generalized Kernel Regularized Least Squares</atitle><jtitle>arXiv.org</jtitle><date>2023-09-08</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Kernel Regularized Least Squares (KRLS) is a popular method for flexibly estimating models that may have complex relationships between variables. However, its usefulness to many researchers is limited for two reasons. First, existing approaches are inflexible and do not allow KRLS to be combined with theoretically-motivated extensions such as random effects, unregularized fixed effects, or non-Gaussian outcomes. Second, estimation is extremely computationally intensive for even modestly sized datasets. Our paper addresses both concerns by introducing generalized KRLS (gKRLS). We note that KRLS can be re-formulated as a hierarchical model thereby allowing easy inference and modular model construction where KRLS can be used alongside random effects, splines, and unregularized fixed effects. Computationally, we also implement random sketching to dramatically accelerate estimation while incurring a limited penalty in estimation quality. We demonstrate that gKRLS can be fit on datasets with tens of thousands of observations in under one minute. Further, state-of-the-art techniques that require fitting the model over a dozen times (e.g. meta-learners) can be estimated quickly.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2209.14355</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-09
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2209_14355
source arXiv.org; Free E- Journals
subjects Complex variables
Computer Science - Learning
Datasets
Estimation
Kernels
Least squares
Modular construction
Statistics - Applications
Statistics - Machine Learning
title Generalized Kernel Regularized Least Squares
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T10%3A21%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Generalized%20Kernel%20Regularized%20Least%20Squares&rft.jtitle=arXiv.org&rft.au=Chang,%20Qing&rft.date=2023-09-08&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2209.14355&rft_dat=%3Cproquest_arxiv%3E2719593866%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2719593866&rft_id=info:pmid/&rfr_iscdi=true