Label switching problem in Bayesian analysis for gravitational wave astronomy
The label switching problem arises in the Bayesian analysis of models containing multiple indistinguishable parameters with arbitrary ordering. Any permutation of these parameters is equivalent, therefore models with many such parameters have extremely multimodal posterior distributions. It is diffi...
Gespeichert in:
| Veröffentlicht in: | Physical review. D 2019-10, Vol.100 (8), Article 084041 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 8 |
| container_start_page | |
| container_title | Physical review. D |
| container_volume | 100 |
| creator | Buscicchio, Riccardo Roebber, Elinore Goldstein, Janna M. Moore, Christopher J. |
| description | The label switching problem arises in the Bayesian analysis of models containing multiple indistinguishable parameters with arbitrary ordering. Any permutation of these parameters is equivalent, therefore models with many such parameters have extremely multimodal posterior distributions. It is difficult to sample efficiently from such posteriors. This paper discusses a solution to this problem which involves carefully mapping the input parameter space to a high dimensional hypertriangle. It is demonstrated that this solution is efficient even for large numbers of parameters and can be easily applied alongside any stochastic sampling algorithm. This method is illustrated using two example problems from the field of gravitational wave astronomy. |
| doi_str_mv | 10.1103/PhysRevD.100.084041 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2316407585</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2316407585</sourcerecordid><originalsourceid>FETCH-LOGICAL-c388t-d345332ab4a940f80f9ef0b591baed723c6340e0defbff1b6c4e55adde2ec5f23</originalsourceid><addsrcrecordid>eNo9kFtLw0AUhBdRsNT-Al8WfE49m93N5VHrFSqK6HM4m5xtt6RJ3U1T8u-NVH2aYRiG4WPsUsBcCJDXb-shvFN_NxcAc8gUKHHCJrFKIQKI89N_L-CczULYwGgTyFMhJuxliYZqHg6uK9euWfGdb01NW-4afosDBYcNxwbrIbjAbev5ymPvOuxcO6b8gD1xDJ1vm3Y7XLAzi3Wg2a9O2efD_cfiKVq-Pj4vbpZRKbOsiyqptJQxGoW5ApuBzcmC0bkwSFUayzKRCggqssZaYZJSkdZYVRRTqW0sp-zquDu-_dpT6IpNu_fjn1DEUiQKUp3psSWPrdK3IXiyxc67LfqhEFD8oCv-0I0BFEd08htzxmTx</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2316407585</pqid></control><display><type>article</type><title>Label switching problem in Bayesian analysis for gravitational wave astronomy</title><source>American Physical Society Journals</source><creator>Buscicchio, Riccardo ; Roebber, Elinore ; Goldstein, Janna M. ; Moore, Christopher J.</creator><creatorcontrib>Buscicchio, Riccardo ; Roebber, Elinore ; Goldstein, Janna M. ; Moore, Christopher J.</creatorcontrib><description>The label switching problem arises in the Bayesian analysis of models containing multiple indistinguishable parameters with arbitrary ordering. Any permutation of these parameters is equivalent, therefore models with many such parameters have extremely multimodal posterior distributions. It is difficult to sample efficiently from such posteriors. This paper discusses a solution to this problem which involves carefully mapping the input parameter space to a high dimensional hypertriangle. It is demonstrated that this solution is efficient even for large numbers of parameters and can be easily applied alongside any stochastic sampling algorithm. This method is illustrated using two example problems from the field of gravitational wave astronomy.</description><identifier>ISSN: 2470-0010</identifier><identifier>EISSN: 2470-0029</identifier><identifier>DOI: 10.1103/PhysRevD.100.084041</identifier><language>eng</language><publisher>College Park: American Physical Society</publisher><subject>Algorithms ; Astronomical models ; Astronomy ; Bayesian analysis ; Gravitation ; Gravitational waves ; Mapping ; Monte Carlo simulation ; Parameters ; Permutations ; Switching</subject><ispartof>Physical review. D, 2019-10, Vol.100 (8), Article 084041</ispartof><rights>Copyright American Physical Society Oct 15, 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c388t-d345332ab4a940f80f9ef0b591baed723c6340e0defbff1b6c4e55adde2ec5f23</citedby><cites>FETCH-LOGICAL-c388t-d345332ab4a940f80f9ef0b591baed723c6340e0defbff1b6c4e55adde2ec5f23</cites><orcidid>0000-0002-5709-4840 ; 0000-0003-4177-0098 ; 0000-0002-7387-6754 ; 0000-0002-2527-0213</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,2863,2864,27901,27902</link.rule.ids></links><search><creatorcontrib>Buscicchio, Riccardo</creatorcontrib><creatorcontrib>Roebber, Elinore</creatorcontrib><creatorcontrib>Goldstein, Janna M.</creatorcontrib><creatorcontrib>Moore, Christopher J.</creatorcontrib><title>Label switching problem in Bayesian analysis for gravitational wave astronomy</title><title>Physical review. D</title><description>The label switching problem arises in the Bayesian analysis of models containing multiple indistinguishable parameters with arbitrary ordering. Any permutation of these parameters is equivalent, therefore models with many such parameters have extremely multimodal posterior distributions. It is difficult to sample efficiently from such posteriors. This paper discusses a solution to this problem which involves carefully mapping the input parameter space to a high dimensional hypertriangle. It is demonstrated that this solution is efficient even for large numbers of parameters and can be easily applied alongside any stochastic sampling algorithm. This method is illustrated using two example problems from the field of gravitational wave astronomy.</description><subject>Algorithms</subject><subject>Astronomical models</subject><subject>Astronomy</subject><subject>Bayesian analysis</subject><subject>Gravitation</subject><subject>Gravitational waves</subject><subject>Mapping</subject><subject>Monte Carlo simulation</subject><subject>Parameters</subject><subject>Permutations</subject><subject>Switching</subject><issn>2470-0010</issn><issn>2470-0029</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNo9kFtLw0AUhBdRsNT-Al8WfE49m93N5VHrFSqK6HM4m5xtt6RJ3U1T8u-NVH2aYRiG4WPsUsBcCJDXb-shvFN_NxcAc8gUKHHCJrFKIQKI89N_L-CczULYwGgTyFMhJuxliYZqHg6uK9euWfGdb01NW-4afosDBYcNxwbrIbjAbev5ymPvOuxcO6b8gD1xDJ1vm3Y7XLAzi3Wg2a9O2efD_cfiKVq-Pj4vbpZRKbOsiyqptJQxGoW5ApuBzcmC0bkwSFUayzKRCggqssZaYZJSkdZYVRRTqW0sp-zquDu-_dpT6IpNu_fjn1DEUiQKUp3psSWPrdK3IXiyxc67LfqhEFD8oCv-0I0BFEd08htzxmTx</recordid><startdate>20191021</startdate><enddate>20191021</enddate><creator>Buscicchio, Riccardo</creator><creator>Roebber, Elinore</creator><creator>Goldstein, Janna M.</creator><creator>Moore, Christopher J.</creator><general>American Physical Society</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-5709-4840</orcidid><orcidid>https://orcid.org/0000-0003-4177-0098</orcidid><orcidid>https://orcid.org/0000-0002-7387-6754</orcidid><orcidid>https://orcid.org/0000-0002-2527-0213</orcidid></search><sort><creationdate>20191021</creationdate><title>Label switching problem in Bayesian analysis for gravitational wave astronomy</title><author>Buscicchio, Riccardo ; Roebber, Elinore ; Goldstein, Janna M. ; Moore, Christopher J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c388t-d345332ab4a940f80f9ef0b591baed723c6340e0defbff1b6c4e55adde2ec5f23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Astronomical models</topic><topic>Astronomy</topic><topic>Bayesian analysis</topic><topic>Gravitation</topic><topic>Gravitational waves</topic><topic>Mapping</topic><topic>Monte Carlo simulation</topic><topic>Parameters</topic><topic>Permutations</topic><topic>Switching</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Buscicchio, Riccardo</creatorcontrib><creatorcontrib>Roebber, Elinore</creatorcontrib><creatorcontrib>Goldstein, Janna M.</creatorcontrib><creatorcontrib>Moore, Christopher J.</creatorcontrib><collection>CrossRef</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Physical review. D</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Buscicchio, Riccardo</au><au>Roebber, Elinore</au><au>Goldstein, Janna M.</au><au>Moore, Christopher J.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Label switching problem in Bayesian analysis for gravitational wave astronomy</atitle><jtitle>Physical review. D</jtitle><date>2019-10-21</date><risdate>2019</risdate><volume>100</volume><issue>8</issue><artnum>084041</artnum><issn>2470-0010</issn><eissn>2470-0029</eissn><abstract>The label switching problem arises in the Bayesian analysis of models containing multiple indistinguishable parameters with arbitrary ordering. Any permutation of these parameters is equivalent, therefore models with many such parameters have extremely multimodal posterior distributions. It is difficult to sample efficiently from such posteriors. This paper discusses a solution to this problem which involves carefully mapping the input parameter space to a high dimensional hypertriangle. It is demonstrated that this solution is efficient even for large numbers of parameters and can be easily applied alongside any stochastic sampling algorithm. This method is illustrated using two example problems from the field of gravitational wave astronomy.</abstract><cop>College Park</cop><pub>American Physical Society</pub><doi>10.1103/PhysRevD.100.084041</doi><orcidid>https://orcid.org/0000-0002-5709-4840</orcidid><orcidid>https://orcid.org/0000-0003-4177-0098</orcidid><orcidid>https://orcid.org/0000-0002-7387-6754</orcidid><orcidid>https://orcid.org/0000-0002-2527-0213</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2470-0010 |
| ispartof | Physical review. D, 2019-10, Vol.100 (8), Article 084041 |
| issn | 2470-0010 2470-0029 |
| language | eng |
| recordid | cdi_proquest_journals_2316407585 |
| source | American Physical Society Journals |
| subjects | Algorithms Astronomical models Astronomy Bayesian analysis Gravitation Gravitational waves Mapping Monte Carlo simulation Parameters Permutations Switching |
| title | Label switching problem in Bayesian analysis for gravitational wave astronomy |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T21%3A12%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Label%20switching%20problem%20in%20Bayesian%20analysis%20for%20gravitational%20wave%20astronomy&rft.jtitle=Physical%20review.%20D&rft.au=Buscicchio,%20Riccardo&rft.date=2019-10-21&rft.volume=100&rft.issue=8&rft.artnum=084041&rft.issn=2470-0010&rft.eissn=2470-0029&rft_id=info:doi/10.1103/PhysRevD.100.084041&rft_dat=%3Cproquest_cross%3E2316407585%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2316407585&rft_id=info:pmid/&rfr_iscdi=true |