Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive lower bounds for several specific parallel optimization settings...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| 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 | Woodworth, Blake Wang, Jialei Smith, Adam McMahan, Brendan Srebro, Nathan |
| description | We suggest a general oracle-based framework that captures different parallel
stochastic optimization settings described by a dependency graph, and derive
generic lower bounds in terms of this graph. We then use the framework and
derive lower bounds for several specific parallel optimization settings,
including delayed updates and parallel processing with intermittent
communication. We highlight gaps between lower and upper bounds on the oracle
complexity, and cases where the "natural" algorithms are not known to be
optimal. |
| doi_str_mv | 10.48550/arxiv.1805.10222 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1805_10222</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1805_10222</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-a5a19579c40aeb94eb09253874d3d3034cd11305148756ecff293037c171f26f3</originalsourceid><addsrcrecordid>eNotz0tOwzAYBGBvWKDSA7DCByCpn3G8hAoCUlAq0X301w_VkhtHTmiB01MKq9HMYqQPoVtKSlFLSVaQP8OxpDWRJSWMsWu0aTKMe9xlMNHht2RdnO5xm04u48f0Mdhzg8HiBsYJ-5TxBjLE6CJ-n5PZwzQHg7txDofwDXNIww268hAnt_zPBdo-P23XL0XbNa_rh7aASrECJFAtlTaCgNtp4XZEM8lrJSy3nHBhLKWcSCpqJStnvGf6PCtDFfWs8nyB7v5uL6R-zOEA-av_pfUXGv8BZR5H0w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization</title><source>arXiv.org</source><creator>Woodworth, Blake ; Wang, Jialei ; Smith, Adam ; McMahan, Brendan ; Srebro, Nathan</creator><creatorcontrib>Woodworth, Blake ; Wang, Jialei ; Smith, Adam ; McMahan, Brendan ; Srebro, Nathan</creatorcontrib><description>We suggest a general oracle-based framework that captures different parallel
stochastic optimization settings described by a dependency graph, and derive
generic lower bounds in terms of this graph. We then use the framework and
derive lower bounds for several specific parallel optimization settings,
including delayed updates and parallel processing with intermittent
communication. We highlight gaps between lower and upper bounds on the oracle
complexity, and cases where the "natural" algorithms are not known to be
optimal.</description><identifier>DOI: 10.48550/arxiv.1805.10222</identifier><language>eng</language><subject>Computer Science - Learning ; Mathematics - Optimization and Control ; Statistics - Machine Learning</subject><creationdate>2018-05</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/1805.10222$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1805.10222$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Woodworth, Blake</creatorcontrib><creatorcontrib>Wang, Jialei</creatorcontrib><creatorcontrib>Smith, Adam</creatorcontrib><creatorcontrib>McMahan, Brendan</creatorcontrib><creatorcontrib>Srebro, Nathan</creatorcontrib><title>Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization</title><description>We suggest a general oracle-based framework that captures different parallel
stochastic optimization settings described by a dependency graph, and derive
generic lower bounds in terms of this graph. We then use the framework and
derive lower bounds for several specific parallel optimization settings,
including delayed updates and parallel processing with intermittent
communication. We highlight gaps between lower and upper bounds on the oracle
complexity, and cases where the "natural" algorithms are not known to be
optimal.</description><subject>Computer Science - Learning</subject><subject>Mathematics - Optimization and Control</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz0tOwzAYBGBvWKDSA7DCByCpn3G8hAoCUlAq0X301w_VkhtHTmiB01MKq9HMYqQPoVtKSlFLSVaQP8OxpDWRJSWMsWu0aTKMe9xlMNHht2RdnO5xm04u48f0Mdhzg8HiBsYJ-5TxBjLE6CJ-n5PZwzQHg7txDofwDXNIww268hAnt_zPBdo-P23XL0XbNa_rh7aASrECJFAtlTaCgNtp4XZEM8lrJSy3nHBhLKWcSCpqJStnvGf6PCtDFfWs8nyB7v5uL6R-zOEA-av_pfUXGv8BZR5H0w</recordid><startdate>20180525</startdate><enddate>20180525</enddate><creator>Woodworth, Blake</creator><creator>Wang, Jialei</creator><creator>Smith, Adam</creator><creator>McMahan, Brendan</creator><creator>Srebro, Nathan</creator><scope>AKY</scope><scope>AKZ</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20180525</creationdate><title>Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization</title><author>Woodworth, Blake ; Wang, Jialei ; Smith, Adam ; McMahan, Brendan ; Srebro, Nathan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-a5a19579c40aeb94eb09253874d3d3034cd11305148756ecff293037c171f26f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Learning</topic><topic>Mathematics - Optimization and Control</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Woodworth, Blake</creatorcontrib><creatorcontrib>Wang, Jialei</creatorcontrib><creatorcontrib>Smith, Adam</creatorcontrib><creatorcontrib>McMahan, Brendan</creatorcontrib><creatorcontrib>Srebro, Nathan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Woodworth, Blake</au><au>Wang, Jialei</au><au>Smith, Adam</au><au>McMahan, Brendan</au><au>Srebro, Nathan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization</atitle><date>2018-05-25</date><risdate>2018</risdate><abstract>We suggest a general oracle-based framework that captures different parallel
stochastic optimization settings described by a dependency graph, and derive
generic lower bounds in terms of this graph. We then use the framework and
derive lower bounds for several specific parallel optimization settings,
including delayed updates and parallel processing with intermittent
communication. We highlight gaps between lower and upper bounds on the oracle
complexity, and cases where the "natural" algorithms are not known to be
optimal.</abstract><doi>10.48550/arxiv.1805.10222</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1805.10222 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1805_10222 |
| source | arXiv.org |
| subjects | Computer Science - Learning Mathematics - Optimization and Control Statistics - Machine Learning |
| title | Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T13%3A22%3A30IST&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=Graph%20Oracle%20Models,%20Lower%20Bounds,%20and%20Gaps%20for%20Parallel%20Stochastic%20Optimization&rft.au=Woodworth,%20Blake&rft.date=2018-05-25&rft_id=info:doi/10.48550/arxiv.1805.10222&rft_dat=%3Carxiv_GOX%3E1805_10222%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 |