Distributed online convex optimization with a bandit primal-dual mirror descent push-sum algorithm
The distributed online convex optimization problem with time-varying constraints for multi-agent networks is addressed in this article. The purpose is to optimize a sequence of time-varying global cost functions defined as the accumulated values of local cost functions, also attempt to meet the requ...
Saved in:
| Published in | Neurocomputing (Amsterdam) Vol. 497; pp. 204 - 215 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.08.2022
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0925-2312 1872-8286 |
| DOI | 10.1016/j.neucom.2022.05.024 |
Cover
| Abstract | The distributed online convex optimization problem with time-varying constraints for multi-agent networks is addressed in this article. The purpose is to optimize a sequence of time-varying global cost functions defined as the accumulated values of local cost functions, also attempt to meet the requirement of a sequence of time-varying coupled constraint functions which denote the sum of local constraint functions. Cost functions and constraint functions are unknown to agents beforehand. It is supposed that each agent in the network communicates with its neighbours through a uniformly strongly connected sequence of time-varying directed communication topologies. This paper proposes the bandit distributed primal-dual mirror descent push-sum (BDPDMDPS) algorithm constructed by bandit primal-dual, mirror descent and push-sum methods. Operational performance of the presented algorithm is measured by expected regret and expected constraint violation, both of which are proved to be sublinear with respect to the total iteration span T in this paper. Finally, a numerical simulation example is shown, which confirms the results for expected regret and expected constraint violation of BDPDMDPS algorithm. |
|---|---|
| AbstractList | The distributed online convex optimization problem with time-varying constraints for multi-agent networks is addressed in this article. The purpose is to optimize a sequence of time-varying global cost functions defined as the accumulated values of local cost functions, also attempt to meet the requirement of a sequence of time-varying coupled constraint functions which denote the sum of local constraint functions. Cost functions and constraint functions are unknown to agents beforehand. It is supposed that each agent in the network communicates with its neighbours through a uniformly strongly connected sequence of time-varying directed communication topologies. This paper proposes the bandit distributed primal-dual mirror descent push-sum (BDPDMDPS) algorithm constructed by bandit primal-dual, mirror descent and push-sum methods. Operational performance of the presented algorithm is measured by expected regret and expected constraint violation, both of which are proved to be sublinear with respect to the total iteration span T in this paper. Finally, a numerical simulation example is shown, which confirms the results for expected regret and expected constraint violation of BDPDMDPS algorithm. |
| Author | Xu, Shengyuan Yuan, Deming Wang, Cong Zhang, Zhengqiang Zhang, Baoyong |
| Author_xml | – sequence: 1 givenname: Cong surname: Wang fullname: Wang, Cong organization: School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China – sequence: 2 givenname: Shengyuan surname: Xu fullname: Xu, Shengyuan email: syxu@njust.edu.cn organization: School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China – sequence: 3 givenname: Deming surname: Yuan fullname: Yuan, Deming organization: School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China – sequence: 4 givenname: Baoyong surname: Zhang fullname: Zhang, Baoyong organization: School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China – sequence: 5 givenname: Zhengqiang surname: Zhang fullname: Zhang, Zhengqiang organization: School of Electrical Engineering and Automation, Qufu Normal University, Rizhao 276826, China |
| BookMark | eNqFkL1OwzAUhS1UJErhDRj8Agm2E6cJAxIqv1IlFpgt59qmrhK7sp3y8_SkLRMDTHc4-o7u-U7RxHmnEbqgJKeEVpfr3OkBfJ8zwlhOeE5YeYSmtJ6zrGZ1NUFT0jCesYKyE3Qa45oQOqesmaL21sYUbDskrbB3nXUag3db_YH9JtnefslkvcPvNq2wxK10yia8CbaXXaYG2eHehuADVjqCdmM0xFUWhx7L7s2HkerP0LGRXdTnP3eGXu_vXhaP2fL54Wlxs8ygIFXKQEkDrDCNIXNZtcDnhSqBF6RRLSgFHKApWwNF05CybCtNDSF1YSo-RryGYobKQy8EH2PQRuzfDJ-CErHzJNbi4EnsPAnCxehpxK5-YWDTfnQK0nb_wdcHWI_DtlYHEcFqB1rZoCEJ5e3fBd_9gIxP |
| CitedBy_id | crossref_primary_10_1016_j_neunet_2024_106291 crossref_primary_10_1007_s12555_023_0211_3 crossref_primary_10_1109_TNSE_2024_3409061 crossref_primary_10_3390_math10244689 crossref_primary_10_1016_j_knosys_2024_112582 crossref_primary_10_1049_cth2_12548 crossref_primary_10_1016_j_neucom_2024_127789 crossref_primary_10_1016_j_neucom_2024_128213 crossref_primary_10_1109_ACCESS_2023_3244070 crossref_primary_10_1016_j_amc_2023_127865 crossref_primary_10_3390_pr11051416 crossref_primary_10_1080_24725854_2024_2428652 crossref_primary_10_1109_ACCESS_2023_3305529 |
| Cites_doi | 10.1109/TCYB.2020.2999309 10.1109/TAC.2011.2161027 10.1109/TAC.2017.2650563 10.1109/TAC.2018.2860546 10.1109/TAC.2020.2987379 10.1016/j.neucom.2020.05.006 10.1109/TAC.2020.3030743 10.1109/TAC.2014.2364096 10.1109/TSP.2020.2964200 10.1016/S0167-6377(02)00231-6 10.1109/TAC.2017.2743462 10.1109/TCNS.2016.2573639 10.1109/TAC.2020.3021011 10.1109/TAC.2016.2529285 10.1109/TAC.2020.3030883 10.1109/TCYB.2017.2755720 10.1016/j.neucom.2015.12.017 10.1109/TAC.2008.2009515 10.1109/TNSE.2014.2363554 10.1016/j.neucom.2017.01.021 10.1109/TCYB.2020.2990796 10.1109/TCNS.2015.2505149 10.1016/j.automatica.2017.12.053 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier B.V. |
| Copyright_xml | – notice: 2022 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.neucom.2022.05.024 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-8286 |
| EndPage | 215 |
| ExternalDocumentID | 10_1016_j_neucom_2022_05_024 S0925231222005562 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC SEW WUQ XPP ~HD |
| ID | FETCH-LOGICAL-c306t-cdafc23f9f07a6bc573d4c5309dbcddc5cc94bfc399044b6e1f0083f65c5c58c3 |
| IEDL.DBID | .~1 |
| ISSN | 0925-2312 |
| IngestDate | Thu Apr 24 22:49:22 EDT 2025 Thu Oct 16 04:34:39 EDT 2025 Fri Feb 23 02:40:24 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Time-varying constraint Bandit feedback Distributed online convex optimization Time-varying directed network topology |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c306t-cdafc23f9f07a6bc573d4c5309dbcddc5cc94bfc399044b6e1f0083f65c5c58c3 |
| PageCount | 12 |
| ParticipantIDs | crossref_primary_10_1016_j_neucom_2022_05_024 crossref_citationtrail_10_1016_j_neucom_2022_05_024 elsevier_sciencedirect_doi_10_1016_j_neucom_2022_05_024 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-08-01 2022-08-00 |
| PublicationDateYYYYMMDD | 2022-08-01 |
| PublicationDate_xml | – month: 08 year: 2022 text: 2022-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Li, Zhao, Hu, Zhang, Ghosh (b0100) 2020; 407 Mateos-Nnez, Corts (b0025) 2014; 1 Nedic, Olshevsky (b0105) 2015; 60 Nedic, Ozdaglar (b0005) 2009; 54 Duchi, Agarwal, Wainwright (b0010) 2012; 57 Cao, Zhang, Poor (b0095) 2021; 66 Q. L, H. Li, D. Xia, Distributed optimization of first-order discrete-time multi-agent systems with event-triggered communication, Neurocomputing 235 (2017) 255-263. Akbari, Gharesifard, Linder (b0050) 2019; 64 Tsianos, Lawlor, Rabbat (b0115) 2012 Yuan, Hong, Ho, Xu (b0035) 2021; 66 Yuan, Ho, Jiang (b0055) 2018; 48 Tsianos, Rabbat (b0080) 2016; 2 A.D. Flaxman, A.T. Kalai, H.B. McMahan, Online convex optimization in the bandit setting: gradient descent without a gradient, Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms (SODA), Vancouver, pp. 385–394, 2005. S. Lee, M.M. Zavlanos On the sublinear regret of distributed primal-dual algorithms for online constrained optimization, arXiv preprint. arXiv:1705.11128. Yi, Li, Xie, Johansson (b0065) 2020; 68 Nedic, Olshevsky (b0110) 2016; 61 Lee, Nedic, Raginsky (b0045) 2017; 62 Li, Yi, Xie (b0075) 2021; 66 Li, Chen, Dong, Wu (b0020) 2016; 177 Lee, Nedic, Raginsky (b0040) 2018; 5 Hazen (b0135) 2015 Yi, Li, Yang, Xie, Chai, Johansson (b0090) 2021; 66 Akbari, Gharesifard, Linder (b0120) 2017; 4 Yuan, Hong, Ho, Jiang (b0015) 2018; 90 C. Wang, S. Xu, D. Yuan, D. Yuan, B. Zhang, Z. Zhang, Push-sum distributed online optimization with bandit feedback, IEEE Trans. Cybern. doi: 10.1109/TCYB.2020.2999309. Shahrampour, Jadbabaie (b0030) 2018; 63 Li, Gu, Wu, Huang (b0060) 2022; 52 Beck, Teboulle (b0140) 2003; 31 Shahrampour (10.1016/j.neucom.2022.05.024_b0030) 2018; 63 Lee (10.1016/j.neucom.2022.05.024_b0040) 2018; 5 Tsianos (10.1016/j.neucom.2022.05.024_b0080) 2016; 2 Li (10.1016/j.neucom.2022.05.024_b0100) 2020; 407 Yuan (10.1016/j.neucom.2022.05.024_b0035) 2021; 66 Nedic (10.1016/j.neucom.2022.05.024_b0110) 2016; 61 Yi (10.1016/j.neucom.2022.05.024_b0065) 2020; 68 10.1016/j.neucom.2022.05.024_b0130 Li (10.1016/j.neucom.2022.05.024_b0075) 2021; 66 10.1016/j.neucom.2022.05.024_b0070 Hazen (10.1016/j.neucom.2022.05.024_b0135) 2015 Nedic (10.1016/j.neucom.2022.05.024_b0005) 2009; 54 Tsianos (10.1016/j.neucom.2022.05.024_b0115) 2012 Duchi (10.1016/j.neucom.2022.05.024_b0010) 2012; 57 Mateos-Nnez (10.1016/j.neucom.2022.05.024_b0025) 2014; 1 Li (10.1016/j.neucom.2022.05.024_b0060) 2022; 52 Lee (10.1016/j.neucom.2022.05.024_b0045) 2017; 62 Beck (10.1016/j.neucom.2022.05.024_b0140) 2003; 31 10.1016/j.neucom.2022.05.024_b0085 Nedic (10.1016/j.neucom.2022.05.024_b0105) 2015; 60 Yuan (10.1016/j.neucom.2022.05.024_b0055) 2018; 48 Akbari (10.1016/j.neucom.2022.05.024_b0120) 2017; 4 Yi (10.1016/j.neucom.2022.05.024_b0090) 2021; 66 Li (10.1016/j.neucom.2022.05.024_b0020) 2016; 177 10.1016/j.neucom.2022.05.024_b0125 Yuan (10.1016/j.neucom.2022.05.024_b0015) 2018; 90 Akbari (10.1016/j.neucom.2022.05.024_b0050) 2019; 64 Cao (10.1016/j.neucom.2022.05.024_b0095) 2021; 66 |
| References_xml | – reference: C. Wang, S. Xu, D. Yuan, D. Yuan, B. Zhang, Z. Zhang, Push-sum distributed online optimization with bandit feedback, IEEE Trans. Cybern. doi: 10.1109/TCYB.2020.2999309. – volume: 64 start-page: 1746 year: 2019 end-page: 1752 ident: b0050 article-title: Individual regret bounds for the distributed online alternating direction method of multipliers publication-title: IEEE Trans. Autom. Control – reference: S. Lee, M.M. Zavlanos On the sublinear regret of distributed primal-dual algorithms for online constrained optimization, arXiv preprint. arXiv:1705.11128. – volume: 48 start-page: 3045 year: 2018 end-page: 3055 ident: b0055 article-title: An adaptive primal-dual subgradient algorithm for online distributed constrained optimization publication-title: IEEE Trans. Cybern. – volume: 90 start-page: 196 year: 2018 end-page: 203 ident: b0015 article-title: Optimal distributed stochastic mirror descent for strongly convex optimization publication-title: Automatica – volume: 66 start-page: 5049 year: 2021 end-page: 5064 ident: b0095 article-title: Constrained online convex optimization with feedback delays publication-title: IEEE Trans. Autom. Control – volume: 52 start-page: 1009 year: 2022 end-page: 1020 ident: b0060 article-title: Online learning algorithm for distributed convex optimization with time-varying coupled constraints and bandit feedback publication-title: IEEE Trans. Cybern. – volume: 177 start-page: 643 year: 2016 end-page: 650 ident: b0020 article-title: Distributed mirror descent method for multi-agent optimization with delay publication-title: Neurocomputing – volume: 66 start-page: 4620 year: 2021 end-page: 4635 ident: b0090 article-title: Distributed bandit online convex optimization with time-varying coupled inequality constraints publication-title: IEEE Trans. Autom. Control – volume: 2 start-page: 489 year: 2016 end-page: 506 ident: b0080 article-title: Efficient distributed online prediction and stochastic optimization with approximate distributed averaging publication-title: IEEE Trans. Signal Inf. Process. Netw. – volume: 1 start-page: 23 year: 2014 end-page: 37 ident: b0025 article-title: Distributed online convex optimization over jointly connected digraphs publication-title: IEEE Trans. Netw. Sci. Eng. – volume: 407 start-page: 155 year: 2020 end-page: 162 ident: b0100 article-title: Distributed initialization-free algorithms for multi-agent optimization problems with coupled inequality constraints publication-title: Neurocomputing – volume: 31 start-page: 167 year: 2003 end-page: 175 ident: b0140 article-title: Mirror descent and nonlinear projected sub-gradient methods for convex optimization publication-title: Oper. Res. Lett. – volume: 54 start-page: 48 year: 2009 end-page: 61 ident: b0005 article-title: Distributed subgradient methods for multi-agent optimization publication-title: IEEE Trans. Autom. Control – start-page: 5453 year: 2012 end-page: 5458 ident: b0115 article-title: Push-sum distributed dual averaging for convex optimization, proc publication-title: 51st IEEE Conf. Decis. Control, Maui, Hawaii – volume: 62 start-page: 6407 year: 2017 end-page: 6414 ident: b0045 article-title: Stochastic dual averaging for decentralized online optimization on time-varying communication graphs publication-title: IEEE Trans. Autom. Control – volume: 68 start-page: 731 year: 2020 end-page: 746 ident: b0065 article-title: Distributed online convex optimization with time-varying coupled inequality constraints publication-title: IEEE Trans. Signal Process. – volume: 66 start-page: 714 year: 2021 end-page: 729 ident: b0035 article-title: Distributed mirror descent for online composite optimization publication-title: IEEE Trans. Autom. Control – year: 2015 ident: b0135 article-title: Introduction to online convex optimization – reference: Q. L, H. Li, D. Xia, Distributed optimization of first-order discrete-time multi-agent systems with event-triggered communication, Neurocomputing 235 (2017) 255-263. – reference: A.D. Flaxman, A.T. Kalai, H.B. McMahan, Online convex optimization in the bandit setting: gradient descent without a gradient, Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms (SODA), Vancouver, pp. 385–394, 2005. – volume: 57 start-page: 592 year: 2012 end-page: 606 ident: b0010 article-title: Dual averaging for distributed optimization: convergence analysis and network scaling publication-title: IEEE Trans. Autom. Control – volume: 66 start-page: 3575 year: 2021 end-page: 3591 ident: b0075 article-title: Distributed online optimization for multi-agent networks with coupled inequality constraints publication-title: IEEE Trans. Autom. Control – volume: 60 start-page: 601 year: 2015 end-page: 615 ident: b0105 article-title: Distributed optimization over time-varying directed graphs publication-title: IEEE Trans. Autom. Control – volume: 4 start-page: 417 year: 2017 end-page: 428 ident: b0120 article-title: Distributed online convex optimization on time-varying directed graphs publication-title: IEEE Trans. Control Netw. Syst. – volume: 5 start-page: 34 year: 2018 end-page: 44 ident: b0040 article-title: Coordinate dual averaging for decentralized online optimization with nonseparable global objectives publication-title: IEEE Trans. Control Netw. Syst. – volume: 63 start-page: 714 year: 2018 end-page: 725 ident: b0030 article-title: Distributed online optimization in dynamic environments using mirror descent publication-title: IEEE Trans. Autom. Control – volume: 61 start-page: 3936 year: 2016 end-page: 3947 ident: b0110 article-title: Stochastic gradient-push for strongly convex functions on time-varying directed graphs publication-title: IEEE Trans. Autom. Control – ident: 10.1016/j.neucom.2022.05.024_b0125 doi: 10.1109/TCYB.2020.2999309 – volume: 57 start-page: 592 issue: 3 year: 2012 ident: 10.1016/j.neucom.2022.05.024_b0010 article-title: Dual averaging for distributed optimization: convergence analysis and network scaling publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2011.2161027 – start-page: 5453 year: 2012 ident: 10.1016/j.neucom.2022.05.024_b0115 article-title: Push-sum distributed dual averaging for convex optimization, proc publication-title: 51st IEEE Conf. Decis. Control, Maui, Hawaii – volume: 62 start-page: 6407 issue: 12 year: 2017 ident: 10.1016/j.neucom.2022.05.024_b0045 article-title: Stochastic dual averaging for decentralized online optimization on time-varying communication graphs publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2017.2650563 – year: 2015 ident: 10.1016/j.neucom.2022.05.024_b0135 – volume: 64 start-page: 1746 issue: 4 year: 2019 ident: 10.1016/j.neucom.2022.05.024_b0050 article-title: Individual regret bounds for the distributed online alternating direction method of multipliers publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2018.2860546 – volume: 66 start-page: 714 issue: 2 year: 2021 ident: 10.1016/j.neucom.2022.05.024_b0035 article-title: Distributed mirror descent for online composite optimization publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2020.2987379 – ident: 10.1016/j.neucom.2022.05.024_b0085 – volume: 2 start-page: 489 issue: 4 year: 2016 ident: 10.1016/j.neucom.2022.05.024_b0080 article-title: Efficient distributed online prediction and stochastic optimization with approximate distributed averaging publication-title: IEEE Trans. Signal Inf. Process. Netw. – volume: 407 start-page: 155 year: 2020 ident: 10.1016/j.neucom.2022.05.024_b0100 article-title: Distributed initialization-free algorithms for multi-agent optimization problems with coupled inequality constraints publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.05.006 – volume: 66 start-page: 5049 issue: 11 year: 2021 ident: 10.1016/j.neucom.2022.05.024_b0095 article-title: Constrained online convex optimization with feedback delays publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2020.3030743 – volume: 60 start-page: 601 issue: 3 year: 2015 ident: 10.1016/j.neucom.2022.05.024_b0105 article-title: Distributed optimization over time-varying directed graphs publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2014.2364096 – volume: 68 start-page: 731 year: 2020 ident: 10.1016/j.neucom.2022.05.024_b0065 article-title: Distributed online convex optimization with time-varying coupled inequality constraints publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2020.2964200 – volume: 31 start-page: 167 issue: 3 year: 2003 ident: 10.1016/j.neucom.2022.05.024_b0140 article-title: Mirror descent and nonlinear projected sub-gradient methods for convex optimization publication-title: Oper. Res. Lett. doi: 10.1016/S0167-6377(02)00231-6 – volume: 63 start-page: 714 issue: 3 year: 2018 ident: 10.1016/j.neucom.2022.05.024_b0030 article-title: Distributed online optimization in dynamic environments using mirror descent publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2017.2743462 – volume: 5 start-page: 34 issue: 1 year: 2018 ident: 10.1016/j.neucom.2022.05.024_b0040 article-title: Coordinate dual averaging for decentralized online optimization with nonseparable global objectives publication-title: IEEE Trans. Control Netw. Syst. doi: 10.1109/TCNS.2016.2573639 – volume: 66 start-page: 3575 issue: 8 year: 2021 ident: 10.1016/j.neucom.2022.05.024_b0075 article-title: Distributed online optimization for multi-agent networks with coupled inequality constraints publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2020.3021011 – volume: 61 start-page: 3936 issue: 12 year: 2016 ident: 10.1016/j.neucom.2022.05.024_b0110 article-title: Stochastic gradient-push for strongly convex functions on time-varying directed graphs publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2016.2529285 – volume: 66 start-page: 4620 issue: 10 year: 2021 ident: 10.1016/j.neucom.2022.05.024_b0090 article-title: Distributed bandit online convex optimization with time-varying coupled inequality constraints publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2020.3030883 – volume: 48 start-page: 3045 issue: 11 year: 2018 ident: 10.1016/j.neucom.2022.05.024_b0055 article-title: An adaptive primal-dual subgradient algorithm for online distributed constrained optimization publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2017.2755720 – ident: 10.1016/j.neucom.2022.05.024_b0070 – volume: 177 start-page: 643 year: 2016 ident: 10.1016/j.neucom.2022.05.024_b0020 article-title: Distributed mirror descent method for multi-agent optimization with delay publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.12.017 – volume: 54 start-page: 48 issue: 1 year: 2009 ident: 10.1016/j.neucom.2022.05.024_b0005 article-title: Distributed subgradient methods for multi-agent optimization publication-title: IEEE Trans. Autom. Control doi: 10.1109/TAC.2008.2009515 – volume: 1 start-page: 23 issue: 1 year: 2014 ident: 10.1016/j.neucom.2022.05.024_b0025 article-title: Distributed online convex optimization over jointly connected digraphs publication-title: IEEE Trans. Netw. Sci. Eng. doi: 10.1109/TNSE.2014.2363554 – ident: 10.1016/j.neucom.2022.05.024_b0130 doi: 10.1016/j.neucom.2017.01.021 – volume: 52 start-page: 1009 issue: 2 year: 2022 ident: 10.1016/j.neucom.2022.05.024_b0060 article-title: Online learning algorithm for distributed convex optimization with time-varying coupled constraints and bandit feedback publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2020.2990796 – volume: 4 start-page: 417 issue: 3 year: 2017 ident: 10.1016/j.neucom.2022.05.024_b0120 article-title: Distributed online convex optimization on time-varying directed graphs publication-title: IEEE Trans. Control Netw. Syst. doi: 10.1109/TCNS.2015.2505149 – volume: 90 start-page: 196 year: 2018 ident: 10.1016/j.neucom.2022.05.024_b0015 article-title: Optimal distributed stochastic mirror descent for strongly convex optimization publication-title: Automatica doi: 10.1016/j.automatica.2017.12.053 |
| SSID | ssj0017129 |
| Score | 2.463616 |
| Snippet | The distributed online convex optimization problem with time-varying constraints for multi-agent networks is addressed in this article. The purpose is to... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 204 |
| SubjectTerms | Bandit feedback Distributed online convex optimization Time-varying constraint Time-varying directed network topology |
| Title | Distributed online convex optimization with a bandit primal-dual mirror descent push-sum algorithm |
| URI | https://dx.doi.org/10.1016/j.neucom.2022.05.024 |
| Volume | 497 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier) customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: GBLVA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier SD Complete Freedom Collection [SCCMFC] customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: ACRLP dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals [SCFCJ] customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AIKHN dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect (Elsevier) customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: .~1 dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVLSH databaseName: Elsevier Journals customDbUrl: mediaType: online eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AKRWK dateStart: 19930201 isFulltext: true providerName: Library Specific Holdings |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEF5KvXjxLdZH2YPXtbvJbh7HUi1VsRct9BayL620aYkpePK3u5NHURAFj0l2IMxOZmbD932D0CULDWU64CQKfEt4pCiJtbLE59xEOkw9jwJR-GEcjCb8biqmLTRouDAAq6xzf5XTy2xd3-nV3uytZrPeI409d4pirsCBkFSZhzkPYYrB1ccG5sFC5lV6e54gsLqhz5UYr8ysATPiuUJW6nd6_Ofy9KXkDPfQTt0r4n71OvuoZbIDtNvMYcD1Z3mI5DWo38LgKqNxJX2BSzT5O166jLCoqZYY_rniFEtgshR4BToTcwJcLLyY5fkyx7rSdsKr9dsLcSGK0_nzMndWiyM0Gd48DUaknp1AlDsEFETp1CrPt7GlYRpIJUJfcyV8GmuptFZCqZhLq1x_QjmXgWEWujEbCPdIRMo_Ru1smZkThKVNwzSSzOc24IbFEQWBGGFcKxZwzaIO8huXJaoWFof5FvOkQZC9JpWjE3B0QkXiHN1BZGO1qoQ1_lgfNruRfAuQxOX-Xy1P_215hrbhqsL7naN2ka_NhetBCtktg6yLtvq396PxJ-Gi3lE |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3JSgQxEA0yHvTiLu7m4DVOkk56OYoL43rRgbmFzqYjs9HOgCe_3VQvg4IoeO2koKmuVFWa914hdMISR5mNBUnjyBORGkoyazyJhHCpTXLOKRCF7x_iTlfc9GRvAZ03XBiAVda5v8rpZbaun7Rrb7Yn_X77kWY83KJYKHAgJAV5eFFInsAN7PRjjvNgCeOV4B6XBLY3_LkS5DVyMwCN8FDJSgFPLn6uT19qztUaWqmbRXxWvc86WnCjDbTaDGLA9bncRPoC5G9hcpWzuNK-wCWc_B2PQ0oY1lxLDD9dcY41UFmmeAJCEwMCZCw87BfFuMC2EnfCk9nbCwkxivPB87gIVsMt1L26fDrvkHp4AjHhFjAlxube8MhnniZ5rI1MIiuMjGhmtbHWSGMyob0JDQoVQseOeWjHfCzDkkxNtI1ao_HI7SCsfZ7kqWaR8LFwLEspKMRIF3qxWFiW7qKocZkytbI4DLgYqAZC9qoqRytwtKJSBUfvIjK3mlTKGn_sT5qvob5FiArJ_1fLvX9bHqOlztP9nbq7frjdR8uwUoH_DlBrWszcYWhIpvqoDLhPIRTf5g |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Distributed+online+convex+optimization+with+a+bandit+primal-dual+mirror+descent+push-sum+algorithm&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Wang%2C+Cong&rft.au=Xu%2C+Shengyuan&rft.au=Yuan%2C+Deming&rft.au=Zhang%2C+Baoyong&rft.date=2022-08-01&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=497&rft.spage=204&rft.epage=215&rft_id=info:doi/10.1016%2Fj.neucom.2022.05.024&rft.externalDocID=S0925231222005562 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |