Multiclass learning with margin: exponential rates with no bias-variance trade-off

Multiclass learning with margin: exponential rates with no bias-variance trade-off

We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can b...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vigogna, Stefano, Meanti, Giacomo, De Vito, Ernesto, Rosasco, Lorenzo
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Learning
Statistics - Machine Learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Vigogna, Stefano
Meanti, Giacomo
De Vito, Ernesto
Rosasco, Lorenzo
description We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can be obtained in correspondence of different margin assumptions. With a self-contained and instructive analysis we are able to generalize known results from the binary to the multiclass setting.
doi_str_mv 10.48550/arxiv.2202.01773
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2202_01773</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2202_01773</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-9b9bf3f28fa50b0b37ac19ca2f553ebd0539fa53ed6141e391c0f78641d190ea3</originalsourceid><addsrcrecordid>eNotj8tKAzEYRrNxIdUHcGVeIGMuk8nEnRRv0CJI98OfzJ8aiJmSibW-vbV19S0OfJxDyI3gTdtrze-gHOK-kZLLhgtj1CV5X3-lGn2CeaYJoeSYt_Q71g_6CWUb8z3Fw27KmGuERAtUnM84T9RFmNkeSoTskdYCI7IphCtyESDNeP2_C7J5etwsX9jq7fl1-bBi0BnFrLMuqCD7AJo77pQBL6wHGbRW6EaulT0ihWMnWoHKCs-D6btWjMJyBLUgt-fbU9SwK_Fo_DP8xQ2nOPULe9tLEA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Multiclass learning with margin: exponential rates with no bias-variance trade-off</title><source>arXiv.org</source><creator>Vigogna, Stefano ; Meanti, Giacomo ; De Vito, Ernesto ; Rosasco, Lorenzo</creator><creatorcontrib>Vigogna, Stefano ; Meanti, Giacomo ; De Vito, Ernesto ; Rosasco, Lorenzo</creatorcontrib><description>We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can be obtained in correspondence of different margin assumptions. With a self-contained and instructive analysis we are able to generalize known results from the binary to the multiclass setting.</description><identifier>DOI: 10.48550/arxiv.2202.01773</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2022-02</creationdate><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2202.01773$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2202.01773$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Vigogna, Stefano</creatorcontrib><creatorcontrib>Meanti, Giacomo</creatorcontrib><creatorcontrib>De Vito, Ernesto</creatorcontrib><creatorcontrib>Rosasco, Lorenzo</creatorcontrib><title>Multiclass learning with margin: exponential rates with no bias-variance trade-off</title><description>We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can be obtained in correspondence of different margin assumptions. With a self-contained and instructive analysis we are able to generalize known results from the binary to the multiclass setting.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tKAzEYRrNxIdUHcGVeIGMuk8nEnRRv0CJI98OfzJ8aiJmSibW-vbV19S0OfJxDyI3gTdtrze-gHOK-kZLLhgtj1CV5X3-lGn2CeaYJoeSYt_Q71g_6CWUb8z3Fw27KmGuERAtUnM84T9RFmNkeSoTskdYCI7IphCtyESDNeP2_C7J5etwsX9jq7fl1-bBi0BnFrLMuqCD7AJo77pQBL6wHGbRW6EaulT0ihWMnWoHKCs-D6btWjMJyBLUgt-fbU9SwK_Fo_DP8xQ2nOPULe9tLEA</recordid><startdate>20220203</startdate><enddate>20220203</enddate><creator>Vigogna, Stefano</creator><creator>Meanti, Giacomo</creator><creator>De Vito, Ernesto</creator><creator>Rosasco, Lorenzo</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20220203</creationdate><title>Multiclass learning with margin: exponential rates with no bias-variance trade-off</title><author>Vigogna, Stefano ; Meanti, Giacomo ; De Vito, Ernesto ; Rosasco, Lorenzo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-9b9bf3f28fa50b0b37ac19ca2f553ebd0539fa53ed6141e391c0f78641d190ea3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Vigogna, Stefano</creatorcontrib><creatorcontrib>Meanti, Giacomo</creatorcontrib><creatorcontrib>De Vito, Ernesto</creatorcontrib><creatorcontrib>Rosasco, Lorenzo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Vigogna, Stefano</au><au>Meanti, Giacomo</au><au>De Vito, Ernesto</au><au>Rosasco, Lorenzo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multiclass learning with margin: exponential rates with no bias-variance trade-off</atitle><date>2022-02-03</date><risdate>2022</risdate><abstract>We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can be obtained in correspondence of different margin assumptions. With a self-contained and instructive analysis we are able to generalize known results from the binary to the multiclass setting.</abstract><doi>10.48550/arxiv.2202.01773</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2202.01773
ispartof
issn
language eng
recordid cdi_arxiv_primary_2202_01773
source arXiv.org
subjects Computer Science - Learning
Statistics - Machine Learning
title Multiclass learning with margin: exponential rates with no bias-variance trade-off
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T05%3A52%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multiclass%20learning%20with%20margin:%20exponential%20rates%20with%20no%20bias-variance%20trade-off&rft.au=Vigogna,%20Stefano&rft.date=2022-02-03&rft_id=info:doi/10.48550/arxiv.2202.01773&rft_dat=%3Carxiv_GOX%3E2202_01773%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true