On the Computational Power of Online Gradient Descent

On the Computational Power of Online Gradient Descent

We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings. Our results imply that, under weak complexity-theoretic assumptions, it is impossible to reason efficiently about the fine-grained behav...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2019-02
Hauptverfasser: Chatziafratis, Vaggos, Roughgarden, Tim, Wang, Joshua R
Format: Artikel
Sprache:eng
Schlagworte:
Polynomials
Weight
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 Chatziafratis, Vaggos
Roughgarden, Tim
Wang, Joshua R
description We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings. Our results imply that, under weak complexity-theoretic assumptions, it is impossible to reason efficiently about the fine-grained behavior of online gradient descent.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2073647017</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2073647017</sourcerecordid><originalsourceid>FETCH-proquest_journals_20736470173</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQw9c9TKMlIVXDOzy0oLUksyczPS8xRCMgvTy1SyE9T8M_LycxLVXAvSkzJTM0rUXBJLU4G0jwMrGmJOcWpvFCam0HZzTXE2UO3oCi_sDS1uCQ-K7-0CGhScbyRgbmxmYm5gaG5MXGqAFkhNH0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2073647017</pqid></control><display><type>article</type><title>On the Computational Power of Online Gradient Descent</title><source>Free E- Journals</source><creator>Chatziafratis, Vaggos ; Roughgarden, Tim ; Wang, Joshua R</creator><creatorcontrib>Chatziafratis, Vaggos ; Roughgarden, Tim ; Wang, Joshua R</creatorcontrib><description>We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings. Our results imply that, under weak complexity-theoretic assumptions, it is impossible to reason efficiently about the fine-grained behavior of online gradient descent.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Polynomials ; Weight</subject><ispartof>arXiv.org, 2019-02</ispartof><rights>2019. 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><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>Chatziafratis, Vaggos</creatorcontrib><creatorcontrib>Roughgarden, Tim</creatorcontrib><creatorcontrib>Wang, Joshua R</creatorcontrib><title>On the Computational Power of Online Gradient Descent</title><title>arXiv.org</title><description>We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings. Our results imply that, under weak complexity-theoretic assumptions, it is impossible to reason efficiently about the fine-grained behavior of online gradient descent.</description><subject>Polynomials</subject><subject>Weight</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQw9c9TKMlIVXDOzy0oLUksyczPS8xRCMgvTy1SyE9T8M_LycxLVXAvSkzJTM0rUXBJLU4G0jwMrGmJOcWpvFCam0HZzTXE2UO3oCi_sDS1uCQ-K7-0CGhScbyRgbmxmYm5gaG5MXGqAFkhNH0</recordid><startdate>20190206</startdate><enddate>20190206</enddate><creator>Chatziafratis, Vaggos</creator><creator>Roughgarden, Tim</creator><creator>Wang, Joshua R</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>20190206</creationdate><title>On the Computational Power of Online Gradient Descent</title><author>Chatziafratis, Vaggos ; Roughgarden, Tim ; Wang, Joshua R</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20736470173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Polynomials</topic><topic>Weight</topic><toplevel>online_resources</toplevel><creatorcontrib>Chatziafratis, Vaggos</creatorcontrib><creatorcontrib>Roughgarden, Tim</creatorcontrib><creatorcontrib>Wang, Joshua R</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>Access via ProQuest (Open Access)</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>Chatziafratis, Vaggos</au><au>Roughgarden, Tim</au><au>Wang, Joshua R</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>On the Computational Power of Online Gradient Descent</atitle><jtitle>arXiv.org</jtitle><date>2019-02-06</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings. Our results imply that, under weak complexity-theoretic assumptions, it is impossible to reason efficiently about the fine-grained behavior of online gradient descent.</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, 2019-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2073647017
source Free E- Journals
subjects Polynomials
Weight
title On the Computational Power of Online Gradient Descent
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T16%3A47%3A47IST&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=On%20the%20Computational%20Power%20of%20Online%20Gradient%20Descent&rft.jtitle=arXiv.org&rft.au=Chatziafratis,%20Vaggos&rft.date=2019-02-06&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2073647017%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2073647017&rft_id=info:pmid/&rfr_iscdi=true