Stabilizing black-box model selection with the inflated argmax

Model selection is the process of choosing from a class of candidate models given data. For instance, methods such as the LASSO and sparse identification of nonlinear dynamics (SINDy) formulate model selection as finding a sparse solution to a linear system of equations determined by training data....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-10
Hauptverfasser: Adrian, Melissa, Soloff, Jake A, Willett, Rebecca
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 Adrian, Melissa
Soloff, Jake A
Willett, Rebecca
description Model selection is the process of choosing from a class of candidate models given data. For instance, methods such as the LASSO and sparse identification of nonlinear dynamics (SINDy) formulate model selection as finding a sparse solution to a linear system of equations determined by training data. However, absent strong assumptions, such methods are highly unstable: if a single data point is removed from the training set, a different model may be selected. This paper presents a new approach to stabilizing model selection that leverages a combination of bagging and an "inflated" argmax operation. Our method selects a small collection of models that all fit the data, and it is stable in that, with high probability, the removal of any training point will result in a collection of selected models that overlaps with the original collection. In addition to developing theoretical guarantees, we illustrate this method in (a) a simulation in which strongly correlated covariates make standard LASSO model selection highly unstable and (b) a Lotka-Volterra model selection problem focused on identifying how competition in an ecosystem influences species' abundances. In both settings, the proposed method yields stable and compact collections of selected models, outperforming a variety of benchmarks.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3120693202</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3120693202</sourcerecordid><originalsourceid>FETCH-proquest_journals_31206932023</originalsourceid><addsrcrecordid>eNqNyrEOgjAUQNHGxESi_MNLnJuUV0FdXIzGXXdS4AHF0iotkfj1OvgBTnc4d8YilDLhuw3igsXed0IIzLaYpjJih2tQhTb6rW0DhVHlnRdugt5VZMCToTJoZ-GlQwuhJdC2NipQBWpoejWt2LxWxlP865Ktz6fb8cIfg3uO5EPeuXGwX8plgiLbSxQo_7s-0y04aQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3120693202</pqid></control><display><type>article</type><title>Stabilizing black-box model selection with the inflated argmax</title><source>Free E- Journals</source><creator>Adrian, Melissa ; Soloff, Jake A ; Willett, Rebecca</creator><creatorcontrib>Adrian, Melissa ; Soloff, Jake A ; Willett, Rebecca</creatorcontrib><description>Model selection is the process of choosing from a class of candidate models given data. For instance, methods such as the LASSO and sparse identification of nonlinear dynamics (SINDy) formulate model selection as finding a sparse solution to a linear system of equations determined by training data. However, absent strong assumptions, such methods are highly unstable: if a single data point is removed from the training set, a different model may be selected. This paper presents a new approach to stabilizing model selection that leverages a combination of bagging and an "inflated" argmax operation. Our method selects a small collection of models that all fit the data, and it is stable in that, with high probability, the removal of any training point will result in a collection of selected models that overlaps with the original collection. In addition to developing theoretical guarantees, we illustrate this method in (a) a simulation in which strongly correlated covariates make standard LASSO model selection highly unstable and (b) a Lotka-Volterra model selection problem focused on identifying how competition in an ecosystem influences species' abundances. In both settings, the proposed method yields stable and compact collections of selected models, outperforming a variety of benchmarks.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Data points ; Dynamical systems ; Linear systems ; Mathematical models ; Nonlinear dynamics</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Adrian, Melissa</creatorcontrib><creatorcontrib>Soloff, Jake A</creatorcontrib><creatorcontrib>Willett, Rebecca</creatorcontrib><title>Stabilizing black-box model selection with the inflated argmax</title><title>arXiv.org</title><description>Model selection is the process of choosing from a class of candidate models given data. For instance, methods such as the LASSO and sparse identification of nonlinear dynamics (SINDy) formulate model selection as finding a sparse solution to a linear system of equations determined by training data. However, absent strong assumptions, such methods are highly unstable: if a single data point is removed from the training set, a different model may be selected. This paper presents a new approach to stabilizing model selection that leverages a combination of bagging and an "inflated" argmax operation. Our method selects a small collection of models that all fit the data, and it is stable in that, with high probability, the removal of any training point will result in a collection of selected models that overlaps with the original collection. In addition to developing theoretical guarantees, we illustrate this method in (a) a simulation in which strongly correlated covariates make standard LASSO model selection highly unstable and (b) a Lotka-Volterra model selection problem focused on identifying how competition in an ecosystem influences species' abundances. In both settings, the proposed method yields stable and compact collections of selected models, outperforming a variety of benchmarks.</description><subject>Data points</subject><subject>Dynamical systems</subject><subject>Linear systems</subject><subject>Mathematical models</subject><subject>Nonlinear dynamics</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyrEOgjAUQNHGxESi_MNLnJuUV0FdXIzGXXdS4AHF0iotkfj1OvgBTnc4d8YilDLhuw3igsXed0IIzLaYpjJih2tQhTb6rW0DhVHlnRdugt5VZMCToTJoZ-GlQwuhJdC2NipQBWpoejWt2LxWxlP865Ktz6fb8cIfg3uO5EPeuXGwX8plgiLbSxQo_7s-0y04aQ</recordid><startdate>20241023</startdate><enddate>20241023</enddate><creator>Adrian, Melissa</creator><creator>Soloff, Jake A</creator><creator>Willett, Rebecca</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>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241023</creationdate><title>Stabilizing black-box model selection with the inflated argmax</title><author>Adrian, Melissa ; Soloff, Jake A ; Willett, Rebecca</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31206932023</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Data points</topic><topic>Dynamical systems</topic><topic>Linear systems</topic><topic>Mathematical models</topic><topic>Nonlinear dynamics</topic><toplevel>online_resources</toplevel><creatorcontrib>Adrian, Melissa</creatorcontrib><creatorcontrib>Soloff, Jake A</creatorcontrib><creatorcontrib>Willett, Rebecca</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>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Adrian, Melissa</au><au>Soloff, Jake A</au><au>Willett, Rebecca</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Stabilizing black-box model selection with the inflated argmax</atitle><jtitle>arXiv.org</jtitle><date>2024-10-23</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Model selection is the process of choosing from a class of candidate models given data. For instance, methods such as the LASSO and sparse identification of nonlinear dynamics (SINDy) formulate model selection as finding a sparse solution to a linear system of equations determined by training data. However, absent strong assumptions, such methods are highly unstable: if a single data point is removed from the training set, a different model may be selected. This paper presents a new approach to stabilizing model selection that leverages a combination of bagging and an "inflated" argmax operation. Our method selects a small collection of models that all fit the data, and it is stable in that, with high probability, the removal of any training point will result in a collection of selected models that overlaps with the original collection. In addition to developing theoretical guarantees, we illustrate this method in (a) a simulation in which strongly correlated covariates make standard LASSO model selection highly unstable and (b) a Lotka-Volterra model selection problem focused on identifying how competition in an ecosystem influences species' abundances. In both settings, the proposed method yields stable and compact collections of selected models, outperforming a variety of benchmarks.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_3120693202
source Free E- Journals
subjects Data points
Dynamical systems
Linear systems
Mathematical models
Nonlinear dynamics
title Stabilizing black-box model selection with the inflated argmax
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T22%3A32%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Stabilizing%20black-box%20model%20selection%20with%20the%20inflated%20argmax&rft.jtitle=arXiv.org&rft.au=Adrian,%20Melissa&rft.date=2024-10-23&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3120693202%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3120693202&rft_id=info:pmid/&rfr_iscdi=true