A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks

We introduce a simple time-triggered protocol to achieve communication-efficient non-Bayesian learning over a network. Specifically, we consider a scenario where a group of agents interact over a graph with the aim of discerning the true state of the world that generates their joint observation prof...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the IEEE Conference on Decision & Control s. 8347 - 8352
Hlavní autoři: Mitra, Aritra, Richards, John A., Sundaram, Shreyas
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2019
ISSN:2576-2370
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We introduce a simple time-triggered protocol to achieve communication-efficient non-Bayesian learning over a network. Specifically, we consider a scenario where a group of agents interact over a graph with the aim of discerning the true state of the world that generates their joint observation profiles. To address this problem, we propose a novel distributed learning rule wherein agents aggregate neighboring beliefs based on a min-protocol, and the inter-communication intervals grow geometrically at a rate a ≥ 1. Despite such sparse communication, we show that each agent is still able to rule out every false hypothesis exponentially fast with probability 1, as long as a is finite. For the special case when communication occurs at every time-step, i.e., when a = 1, we prove that the asymptotic learning rates resulting from our algorithm are network-structure independent, and a strict improvement over existing rates. In contrast, when a>1, our analysis reveals that the asymptotic learning rates vary across agents, and exhibit a non-trivial dependence on the network topology and the relative entropies of the agents' likelihood models. This motivates us to consider the problem of allocating signal structures to agents to maximize appropriate performance metrics. In certain special cases, we show that the eccentricity centrality and the decay centrality of the underlying graph help identify optimal allocations; for more general cases, we bound the deviation from the optimal allocation as a function of the parameter a, and the diameter of the graph.
AbstractList We introduce a simple time-triggered protocol to achieve communication-efficient non-Bayesian learning over a network. Specifically, we consider a scenario where a group of agents interact over a graph with the aim of discerning the true state of the world that generates their joint observation profiles. To address this problem, we propose a novel distributed learning rule wherein agents aggregate neighboring beliefs based on a min-protocol, and the inter-communication intervals grow geometrically at a rate a ≥ 1. Despite such sparse communication, we show that each agent is still able to rule out every false hypothesis exponentially fast with probability 1, as long as a is finite. For the special case when communication occurs at every time-step, i.e., when a = 1, we prove that the asymptotic learning rates resulting from our algorithm are network-structure independent, and a strict improvement over existing rates. In contrast, when a>1, our analysis reveals that the asymptotic learning rates vary across agents, and exhibit a non-trivial dependence on the network topology and the relative entropies of the agents' likelihood models. This motivates us to consider the problem of allocating signal structures to agents to maximize appropriate performance metrics. In certain special cases, we show that the eccentricity centrality and the decay centrality of the underlying graph help identify optimal allocations; for more general cases, we bound the deviation from the optimal allocation as a function of the parameter a, and the diameter of the graph.
Author Mitra, Aritra
Richards, John A.
Sundaram, Shreyas
Author_xml – sequence: 1
  givenname: Aritra
  surname: Mitra
  fullname: Mitra, Aritra
  organization: Purdue University,School of Electrical and Computer Engineering
– sequence: 2
  givenname: John A.
  surname: Richards
  fullname: Richards, John A.
  organization: Sandia National Laboratories
– sequence: 3
  givenname: Shreyas
  surname: Sundaram
  fullname: Sundaram, Shreyas
  organization: Purdue University,School of Electrical and Computer Engineering
BookMark eNotkM1Kw0AUhUdRsK0-gQjzAol3fpLJLGtMVSh1ozuh3KZ36mgyKcmI7dsbsKtzFh_fgTNlF6ELxNidgFQIsPflY6kBpE4lCJtakLZQxRmbCiMLIZQt7DmbyMzkiVQGrth0GL4AlLVaTdjHnJdd2_4EX2P0XUgq53ztKUQ-b3Zd7-Nny13X8-qwH2dD9Ng0R77AIfLViD_gkQaPgS8J--DDjvvAVxR_u_57uGaXDpuBbk45Y--L6q18TpavTy_lfJl4aUxMBCKKIq_tBjYmB3RWO53prdxALWtHeZaJsTujSUjI8q0GGmlNpFBgrtSM3f57PRGt971vsT-uT0-oPxXuVb0
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CDC40024.2019.9029838
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1728113989
9781728113982
EISSN 2576-2370
EndPage 8352
ExternalDocumentID 9029838
Genre orig-research
GroupedDBID 29P
6IE
6IH
6IL
6IN
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i277t-1aaa186c9b0b760af94f454d2b0c2cfe65512b0f74e12056d40e6c94ee3a1a633
IEDL.DBID RIE
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000560779007088&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 06:30:23 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i277t-1aaa186c9b0b760af94f454d2b0c2cfe65512b0f74e12056d40e6c94ee3a1a633
OpenAccessLink https://www.osti.gov/servlets/purl/1639419
PageCount 6
ParticipantIDs ieee_primary_9029838
PublicationCentury 2000
PublicationDate 2019-Dec.
PublicationDateYYYYMMDD 2019-12-01
PublicationDate_xml – month: 12
  year: 2019
  text: 2019-Dec.
PublicationDecade 2010
PublicationTitle Proceedings of the IEEE Conference on Decision & Control
PublicationTitleAbbrev CDC
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0039943
Score 1.8000065
Snippet We introduce a simple time-triggered protocol to achieve communication-efficient non-Bayesian learning over a network. Specifically, we consider a scenario...
SourceID ieee
SourceType Publisher
StartPage 8347
Title A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks
URI https://ieeexplore.ieee.org/document/9029838
WOSCitedRecordID wos000560779007088&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFH9B4kEvfoDxOz14tNCu3UePiBBPCwdNOJiQduuQBIHAMPLf-7pNlMSLSw_N0tctr0nfW_f7_R7AHTPc4uVTnfoplcIYarRilAdZlPksVTKTRbGJMI6j4VANanC_5cKgYQE-sy3XLf7lp_Nk7Y7K2srphYtoD_bCMCi5Wt-7LsZZKSqGDmeq3X3sShd_HHhLtSrDnQoqRQDpH_3v0cfQ_GHikcE2xpxAzc5O4fCXiGADXjtkh-VBe4UqBE5HOtPxHD_-394Jpqak97mYzxw4SE-nG9LXq5zEOPxBb6xjUpJKanVMJjMSl-jwVRNe-r3n7hOtaibQiReGOeVaax4FiTLMhAHTmXO2L1PPsMRLMhtghoT9LJSWe5j8pJJZHC2tFZrrQIgzqM_wZc6BMOFZHycKJDbF0khzP_JMghbCcE9fQMP5abQoZTFGlYsu_759BQduKUokyDXU8-Xa3sB-8pFPVsvbYi2_AP_hoZo
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bT8IwFG4QTdQXL2C82wcfLfS2Sx8RIRhx4QETHkxIu3VIgoPAMPLvbbeJkvji0odm6emW06TnrPu-7wBwixXR5nKQjJwIcaYUUlJgRNzYjx0cCR7zrNiEFwT-YCB6JXC35sIYwwx8pmu2m_3Lj6bh0h6V1YXVC2f-Fth2OKc4Z2t977sm0nJWcHQIFvXmQ5PbCGThW6JWmG7UUMlCSPvgfw8_BNUfLh7sraPMESjp5Bjs_5IRrIDXBtzgeaBWpgthpoONyWhqPv_f3qFJTmHrczZNLDxITiYr2JaLFAZm-L1caculhIXY6giOExjk-PBFFby0W_1mBxVVE9CYel6KiJSS-G4oFFaei2Vs3e3wiCoc0jDWrsmRTD_2uCbUpD8Rx9qM5lozSaTL2AkoJ-ZlTgHEjGrHTORy0wSOfEkcn6rQWDBFqDwDFeun4SwXxhgWLjr_-_YN2O30n7vD7mPwdAH27LLkuJBLUE7nS30FdsKPdLyYX2fr-gWWXKTh
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=proceeding&rft.title=Proceedings+of+the+IEEE+Conference+on+Decision+%26+Control&rft.atitle=A+Communication-Efficient+Algorithm+for+Exponentially+Fast+Non-Bayesian+Learning+in+Networks&rft.au=Mitra%2C+Aritra&rft.au=Richards%2C+John+A.&rft.au=Sundaram%2C+Shreyas&rft.date=2019-12-01&rft.pub=IEEE&rft.eissn=2576-2370&rft.spage=8347&rft.epage=8352&rft_id=info:doi/10.1109%2FCDC40024.2019.9029838&rft.externalDocID=9029838