On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit

In this work, we consider a distributed online convex optimization problem, with time-varying (potentially adversarial) constraints. A set of nodes, jointly aim to minimize a global objective function, which is the sum of local convex functions. The objective and constraint functions are revealed lo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sharma, Pranay, Khanduri, Prashant, Shen, Lixin, BucciJr, Donald J, Varshney, Pramod K
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 Sharma, Pranay
Khanduri, Prashant
Shen, Lixin
BucciJr, Donald J
Varshney, Pramod K
description In this work, we consider a distributed online convex optimization problem, with time-varying (potentially adversarial) constraints. A set of nodes, jointly aim to minimize a global objective function, which is the sum of local convex functions. The objective and constraint functions are revealed locally to the nodes, at each time, after taking an action. Naturally, the constraints cannot be instantaneously satisfied. Therefore, we reformulate the problem to satisfy these constraints in the long term. To this end, we propose a distributed primal-dual mirror descent based approach, in which the primal and dual updates are carried out locally at all the nodes. This is followed by sharing and mixing of the primal variables by the local nodes via communication with the immediate neighbors. To quantify the performance of the proposed algorithm, we utilize the challenging, but more realistic metrics of dynamic regret and fit. Dynamic regret measures the cumulative loss incurred by the algorithm, compared to the best dynamic strategy. On the other hand, fit measures the long term cumulative constraint violations. Without assuming the restrictive Slater's conditions, we show that the proposed algorithm achieves sublinear regret and fit under mild, commonly used assumptions.
doi_str_mv 10.48550/arxiv.2001.03166
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2001_03166</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2001_03166</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-57e7fa4b7981d51f6d3ae9f9ad14a37731005696db5e4a4ae0ba1183ff71f0253</originalsourceid><addsrcrecordid>eNotz81OAjEUhuFuXBj0AlzZG5ixpX8zSzOIkpBMouwnp_ZUT8IUUgqCV28AV9_mzZc8jD1IUevGGPEE-UiHeiqErIWS1t6yvk98RruSye8LBt6nNSXk3SYd8Mj7baGRfqHQJvEfKt_8Y-_PAWQ-OyUY6ZO_41fGwiEFPqdyx24irHd4_78Ttpq_rLq3atm_LrrnZQXW2co4dBG0d20jg5HRBgXYxhaC1KCcU1IIY1sbvEENGlB4kLJRMToZxdSoCXu83l5EwzbTCPk0nGXDRab-AObHSQM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit</title><source>arXiv.org</source><creator>Sharma, Pranay ; Khanduri, Prashant ; Shen, Lixin ; BucciJr, Donald J ; Varshney, Pramod K</creator><creatorcontrib>Sharma, Pranay ; Khanduri, Prashant ; Shen, Lixin ; BucciJr, Donald J ; Varshney, Pramod K</creatorcontrib><description>In this work, we consider a distributed online convex optimization problem, with time-varying (potentially adversarial) constraints. A set of nodes, jointly aim to minimize a global objective function, which is the sum of local convex functions. The objective and constraint functions are revealed locally to the nodes, at each time, after taking an action. Naturally, the constraints cannot be instantaneously satisfied. Therefore, we reformulate the problem to satisfy these constraints in the long term. To this end, we propose a distributed primal-dual mirror descent based approach, in which the primal and dual updates are carried out locally at all the nodes. This is followed by sharing and mixing of the primal variables by the local nodes via communication with the immediate neighbors. To quantify the performance of the proposed algorithm, we utilize the challenging, but more realistic metrics of dynamic regret and fit. Dynamic regret measures the cumulative loss incurred by the algorithm, compared to the best dynamic strategy. On the other hand, fit measures the long term cumulative constraint violations. Without assuming the restrictive Slater's conditions, we show that the proposed algorithm achieves sublinear regret and fit under mild, commonly used assumptions.</description><identifier>DOI: 10.48550/arxiv.2001.03166</identifier><language>eng</language><subject>Computer Science - Distributed, Parallel, and Cluster Computing ; Computer Science - Systems and Control ; Mathematics - Optimization and Control</subject><creationdate>2020-01</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2001.03166$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2001.03166$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Sharma, Pranay</creatorcontrib><creatorcontrib>Khanduri, Prashant</creatorcontrib><creatorcontrib>Shen, Lixin</creatorcontrib><creatorcontrib>BucciJr, Donald J</creatorcontrib><creatorcontrib>Varshney, Pramod K</creatorcontrib><title>On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit</title><description>In this work, we consider a distributed online convex optimization problem, with time-varying (potentially adversarial) constraints. A set of nodes, jointly aim to minimize a global objective function, which is the sum of local convex functions. The objective and constraint functions are revealed locally to the nodes, at each time, after taking an action. Naturally, the constraints cannot be instantaneously satisfied. Therefore, we reformulate the problem to satisfy these constraints in the long term. To this end, we propose a distributed primal-dual mirror descent based approach, in which the primal and dual updates are carried out locally at all the nodes. This is followed by sharing and mixing of the primal variables by the local nodes via communication with the immediate neighbors. To quantify the performance of the proposed algorithm, we utilize the challenging, but more realistic metrics of dynamic regret and fit. Dynamic regret measures the cumulative loss incurred by the algorithm, compared to the best dynamic strategy. On the other hand, fit measures the long term cumulative constraint violations. Without assuming the restrictive Slater's conditions, we show that the proposed algorithm achieves sublinear regret and fit under mild, commonly used assumptions.</description><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><subject>Computer Science - Systems and Control</subject><subject>Mathematics - Optimization and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81OAjEUhuFuXBj0AlzZG5ixpX8zSzOIkpBMouwnp_ZUT8IUUgqCV28AV9_mzZc8jD1IUevGGPEE-UiHeiqErIWS1t6yvk98RruSye8LBt6nNSXk3SYd8Mj7baGRfqHQJvEfKt_8Y-_PAWQ-OyUY6ZO_41fGwiEFPqdyx24irHd4_78Ttpq_rLq3atm_LrrnZQXW2co4dBG0d20jg5HRBgXYxhaC1KCcU1IIY1sbvEENGlB4kLJRMToZxdSoCXu83l5EwzbTCPk0nGXDRab-AObHSQM</recordid><startdate>20200109</startdate><enddate>20200109</enddate><creator>Sharma, Pranay</creator><creator>Khanduri, Prashant</creator><creator>Shen, Lixin</creator><creator>BucciJr, Donald J</creator><creator>Varshney, Pramod K</creator><scope>AKY</scope><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20200109</creationdate><title>On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit</title><author>Sharma, Pranay ; Khanduri, Prashant ; Shen, Lixin ; BucciJr, Donald J ; Varshney, Pramod K</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-57e7fa4b7981d51f6d3ae9f9ad14a37731005696db5e4a4ae0ba1183ff71f0253</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Distributed, Parallel, and Cluster Computing</topic><topic>Computer Science - Systems and Control</topic><topic>Mathematics - Optimization and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Sharma, Pranay</creatorcontrib><creatorcontrib>Khanduri, Prashant</creatorcontrib><creatorcontrib>Shen, Lixin</creatorcontrib><creatorcontrib>BucciJr, Donald J</creatorcontrib><creatorcontrib>Varshney, Pramod K</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sharma, Pranay</au><au>Khanduri, Prashant</au><au>Shen, Lixin</au><au>BucciJr, Donald J</au><au>Varshney, Pramod K</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit</atitle><date>2020-01-09</date><risdate>2020</risdate><abstract>In this work, we consider a distributed online convex optimization problem, with time-varying (potentially adversarial) constraints. A set of nodes, jointly aim to minimize a global objective function, which is the sum of local convex functions. The objective and constraint functions are revealed locally to the nodes, at each time, after taking an action. Naturally, the constraints cannot be instantaneously satisfied. Therefore, we reformulate the problem to satisfy these constraints in the long term. To this end, we propose a distributed primal-dual mirror descent based approach, in which the primal and dual updates are carried out locally at all the nodes. This is followed by sharing and mixing of the primal variables by the local nodes via communication with the immediate neighbors. To quantify the performance of the proposed algorithm, we utilize the challenging, but more realistic metrics of dynamic regret and fit. Dynamic regret measures the cumulative loss incurred by the algorithm, compared to the best dynamic strategy. On the other hand, fit measures the long term cumulative constraint violations. Without assuming the restrictive Slater's conditions, we show that the proposed algorithm achieves sublinear regret and fit under mild, commonly used assumptions.</abstract><doi>10.48550/arxiv.2001.03166</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2001.03166
ispartof
issn
language eng
recordid cdi_arxiv_primary_2001_03166
source arXiv.org
subjects Computer Science - Distributed, Parallel, and Cluster Computing
Computer Science - Systems and Control
Mathematics - Optimization and Control
title On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T15%3A55%3A21IST&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=On%20Distributed%20Online%20Convex%20Optimization%20with%20Sublinear%20Dynamic%20Regret%20and%20Fit&rft.au=Sharma,%20Pranay&rft.date=2020-01-09&rft_id=info:doi/10.48550/arxiv.2001.03166&rft_dat=%3Carxiv_GOX%3E2001_03166%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