On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference
We study the asymptotic learning rates of belief vectors in a distributed hypothesis testing problem under linear and log-linear combination rules. We show that under both combination strategies, agents are able to learn the truth exponentially fast, with a faster rate under log-linear fusion. We ex...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on automatic control 2024-04, Vol.69 (4), p.1-16 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 16 |
|---|---|
| container_issue | 4 |
| container_start_page | 1 |
| container_title | IEEE transactions on automatic control |
| container_volume | 69 |
| creator | Kayaalp, Mert Inan, Yunus Telatar, Emre Sayed, Ali H. |
| description | We study the asymptotic learning rates of belief vectors in a distributed hypothesis testing problem under linear and log-linear combination rules. We show that under both combination strategies, agents are able to learn the truth exponentially fast, with a faster rate under log-linear fusion. We examine the gap between the rates in terms of network connectivity and information diversity. We also provide closed-form expressions for special cases involving federated architectures and exchangeable networks. |
| doi_str_mv | 10.1109/TAC.2023.3330405 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TAC_2023_3330405</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10309154</ieee_id><sourcerecordid>3015042794</sourcerecordid><originalsourceid>FETCH-LOGICAL-c334t-4e4f93069310970471cef5c132a63d16831994e8b45012ad5bb0cd5c5cc3a3053</originalsourceid><addsrcrecordid>eNpNkDFPwzAQhS0EEqWwMzBYYk45--w0HkuhUFGpS5mtxDmrqdqk2MnAv8dVOzCdnu69u6ePsUcBEyHAvGxm84kEiRNEBAX6io2E1kUmtcRrNgIQRWZkkd-yuxh3SeZKiRH7Wre83xKfhabfHqhvHC_bmn9Ql0RIajHEpmt55_kr7Rvykfsu8Lcmpm019FTzZespUOvont34ch_p4TLH7Hvxvpl_Zqv1x3I-W2UOUfWZIuUNQm4w9Z6CmgpHXjuBssyxFnmBwhhFRaU0CFnWuqrA1dpp57BE0Dhmz-e7x9D9DBR7u-uG0KaXFkFoUHJqVHLB2eVCF2Mgb4-hOZTh1wqwJ2Q2IbMnZPaCLEWezpGGiP7ZEYzQCv8A4eBleg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3015042794</pqid></control><display><type>article</type><title>On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference</title><source>IEEE Electronic Library (IEL)</source><creator>Kayaalp, Mert ; Inan, Yunus ; Telatar, Emre ; Sayed, Ali H.</creator><creatorcontrib>Kayaalp, Mert ; Inan, Yunus ; Telatar, Emre ; Sayed, Ali H.</creatorcontrib><description>We study the asymptotic learning rates of belief vectors in a distributed hypothesis testing problem under linear and log-linear combination rules. We show that under both combination strategies, agents are able to learn the truth exponentially fast, with a faster rate under log-linear fusion. We examine the gap between the rates in terms of network connectivity and information diversity. We also provide closed-form expressions for special cases involving federated architectures and exchangeable networks.</description><identifier>ISSN: 0018-9286</identifier><identifier>EISSN: 1558-2523</identifier><identifier>DOI: 10.1109/TAC.2023.3330405</identifier><identifier>CODEN: IETAA9</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Asymptotic decay rate ; Bayes methods ; distributed decision-making ; Estimation ; fusion of belief vectors ; linear and logarithmic opinion pools ; Network topology ; Peer-to-peer computing ; social learning ; Testing ; Topology</subject><ispartof>IEEE transactions on automatic control, 2024-04, Vol.69 (4), p.1-16</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c334t-4e4f93069310970471cef5c132a63d16831994e8b45012ad5bb0cd5c5cc3a3053</citedby><cites>FETCH-LOGICAL-c334t-4e4f93069310970471cef5c132a63d16831994e8b45012ad5bb0cd5c5cc3a3053</cites><orcidid>0000-0002-0082-1058 ; 0000-0002-5125-5519 ; 0009-0007-5365-5368 ; 0000-0001-9725-2455</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10309154$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10309154$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kayaalp, Mert</creatorcontrib><creatorcontrib>Inan, Yunus</creatorcontrib><creatorcontrib>Telatar, Emre</creatorcontrib><creatorcontrib>Sayed, Ali H.</creatorcontrib><title>On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference</title><title>IEEE transactions on automatic control</title><addtitle>TAC</addtitle><description>We study the asymptotic learning rates of belief vectors in a distributed hypothesis testing problem under linear and log-linear combination rules. We show that under both combination strategies, agents are able to learn the truth exponentially fast, with a faster rate under log-linear fusion. We examine the gap between the rates in terms of network connectivity and information diversity. We also provide closed-form expressions for special cases involving federated architectures and exchangeable networks.</description><subject>Asymptotic decay rate</subject><subject>Bayes methods</subject><subject>distributed decision-making</subject><subject>Estimation</subject><subject>fusion of belief vectors</subject><subject>linear and logarithmic opinion pools</subject><subject>Network topology</subject><subject>Peer-to-peer computing</subject><subject>social learning</subject><subject>Testing</subject><subject>Topology</subject><issn>0018-9286</issn><issn>1558-2523</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkDFPwzAQhS0EEqWwMzBYYk45--w0HkuhUFGpS5mtxDmrqdqk2MnAv8dVOzCdnu69u6ePsUcBEyHAvGxm84kEiRNEBAX6io2E1kUmtcRrNgIQRWZkkd-yuxh3SeZKiRH7Wre83xKfhabfHqhvHC_bmn9Ql0RIajHEpmt55_kr7Rvykfsu8Lcmpm019FTzZespUOvont34ch_p4TLH7Hvxvpl_Zqv1x3I-W2UOUfWZIuUNQm4w9Z6CmgpHXjuBssyxFnmBwhhFRaU0CFnWuqrA1dpp57BE0Dhmz-e7x9D9DBR7u-uG0KaXFkFoUHJqVHLB2eVCF2Mgb4-hOZTh1wqwJ2Q2IbMnZPaCLEWezpGGiP7ZEYzQCv8A4eBleg</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Kayaalp, Mert</creator><creator>Inan, Yunus</creator><creator>Telatar, Emre</creator><creator>Sayed, Ali H.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-0082-1058</orcidid><orcidid>https://orcid.org/0000-0002-5125-5519</orcidid><orcidid>https://orcid.org/0009-0007-5365-5368</orcidid><orcidid>https://orcid.org/0000-0001-9725-2455</orcidid></search><sort><creationdate>20240401</creationdate><title>On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference</title><author>Kayaalp, Mert ; Inan, Yunus ; Telatar, Emre ; Sayed, Ali H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c334t-4e4f93069310970471cef5c132a63d16831994e8b45012ad5bb0cd5c5cc3a3053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Asymptotic decay rate</topic><topic>Bayes methods</topic><topic>distributed decision-making</topic><topic>Estimation</topic><topic>fusion of belief vectors</topic><topic>linear and logarithmic opinion pools</topic><topic>Network topology</topic><topic>Peer-to-peer computing</topic><topic>social learning</topic><topic>Testing</topic><topic>Topology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kayaalp, Mert</creatorcontrib><creatorcontrib>Inan, Yunus</creatorcontrib><creatorcontrib>Telatar, Emre</creatorcontrib><creatorcontrib>Sayed, Ali H.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on automatic control</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kayaalp, Mert</au><au>Inan, Yunus</au><au>Telatar, Emre</au><au>Sayed, Ali H.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference</atitle><jtitle>IEEE transactions on automatic control</jtitle><stitle>TAC</stitle><date>2024-04-01</date><risdate>2024</risdate><volume>69</volume><issue>4</issue><spage>1</spage><epage>16</epage><pages>1-16</pages><issn>0018-9286</issn><eissn>1558-2523</eissn><coden>IETAA9</coden><abstract>We study the asymptotic learning rates of belief vectors in a distributed hypothesis testing problem under linear and log-linear combination rules. We show that under both combination strategies, agents are able to learn the truth exponentially fast, with a faster rate under log-linear fusion. We examine the gap between the rates in terms of network connectivity and information diversity. We also provide closed-form expressions for special cases involving federated architectures and exchangeable networks.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TAC.2023.3330405</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0002-0082-1058</orcidid><orcidid>https://orcid.org/0000-0002-5125-5519</orcidid><orcidid>https://orcid.org/0009-0007-5365-5368</orcidid><orcidid>https://orcid.org/0000-0001-9725-2455</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0018-9286 |
| ispartof | IEEE transactions on automatic control, 2024-04, Vol.69 (4), p.1-16 |
| issn | 0018-9286 1558-2523 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_TAC_2023_3330405 |
| source | IEEE Electronic Library (IEL) |
| subjects | Asymptotic decay rate Bayes methods distributed decision-making Estimation fusion of belief vectors linear and logarithmic opinion pools Network topology Peer-to-peer computing social learning Testing Topology |
| title | On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T08%3A14%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=On%20the%20Arithmetic%20and%20Geometric%20Fusion%20of%20Beliefs%20for%20Distributed%20Inference&rft.jtitle=IEEE%20transactions%20on%20automatic%20control&rft.au=Kayaalp,%20Mert&rft.date=2024-04-01&rft.volume=69&rft.issue=4&rft.spage=1&rft.epage=16&rft.pages=1-16&rft.issn=0018-9286&rft.eissn=1558-2523&rft.coden=IETAA9&rft_id=info:doi/10.1109/TAC.2023.3330405&rft_dat=%3Cproquest_RIE%3E3015042794%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3015042794&rft_id=info:pmid/&rft_ieee_id=10309154&rfr_iscdi=true |