A Laplace Mixture Representation of the Horseshoe and Some Implications

The horseshoe prior, defined as a half Cauchy scale mixture of normal, provides a state of the art approach to Bayesian sparse signal recovery. We provide a new representation of the horseshoe density as a scale mixture of the Laplace density, explicitly identifying the mixing measure. Using the cel...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2022, Vol.29, p.2547-2551
Main Authors: Sagar, Ksheera, Bhadra, Anindya
Format: Article
Language:English
Subjects:
Algorithms
Bayesian sparse signal recovery
Bernstein–Widder
completely monotone function
Concavity
Convergence
Density
Estimation
Linear approximation
local linear approximation
Mathematical models
Mixtures
Optimization
Random variables
Representations
Signal reconstruction
Tail
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c333t-65edc0577ae34251f08aa2cbb8ab76851d1e3d50d4f29be65ea5f37f5a80f3183
cites cdi_FETCH-LOGICAL-c333t-65edc0577ae34251f08aa2cbb8ab76851d1e3d50d4f29be65ea5f37f5a80f3183
container_end_page 2551
container_issue
container_start_page 2547
container_title IEEE signal processing letters
container_volume 29
creator Sagar, Ksheera
Bhadra, Anindya
description The horseshoe prior, defined as a half Cauchy scale mixture of normal, provides a state of the art approach to Bayesian sparse signal recovery. We provide a new representation of the horseshoe density as a scale mixture of the Laplace density, explicitly identifying the mixing measure. Using the celebrated Bernstein-Widder theorem and a result due to Bochner, our representation immediately establishes the complete monotonicity of the horseshoe density and strong concavity of the corresponding penalty. Consequently, the equivalence between local linear approximation and expectation-maximization algorithms for finding the posterior mode under the horseshoe penalized regression is established. Further, the resultant estimate is shown to be sparse.
doi_str_mv 10.1109/LSP.2022.3228491
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_9979805</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9979805</ieee_id><sourcerecordid>2757177876</sourcerecordid><originalsourceid>FETCH-LOGICAL-c333t-65edc0577ae34251f08aa2cbb8ab76851d1e3d50d4f29be65ea5f37f5a80f3183</originalsourceid><addsrcrecordid>eNo9kMFLwzAUxoMoOKd3wUvAc-dLsjTJcQzdhIri9BzS9oV1bE1NOtD_3s4NT-87_L7vwY-QWwYTxsA8FKu3CQfOJ4JzPTXsjIyYlDrjImfnQwYFmTGgL8lVShsA0EzLEVnMaOG6rauQvjTf_T4ifccuYsK2d30TWho87ddIlyEmTOuA1LU1XYUd0uddt22qPypdkwvvtglvTndMPp8eP-bLrHhdPM9nRVYJIfosl1hXIJVyKKZcMg_aOV6VpXalyrVkNUNRS6innpsSB9xJL5SXToMXTIsxuT_udjF87TH1dhP2sR1eWq6kYkpplQ8UHKkqhpQietvFZufij2VgD7rsoMsedNmTrqFyd6w0iPiPG6OMBil-Ae97ZcE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2757177876</pqid></control><display><type>article</type><title>A Laplace Mixture Representation of the Horseshoe and Some Implications</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Sagar, Ksheera ; Bhadra, Anindya</creator><creatorcontrib>Sagar, Ksheera ; Bhadra, Anindya</creatorcontrib><description>The horseshoe prior, defined as a half Cauchy scale mixture of normal, provides a state of the art approach to Bayesian sparse signal recovery. We provide a new representation of the horseshoe density as a scale mixture of the Laplace density, explicitly identifying the mixing measure. Using the celebrated Bernstein-Widder theorem and a result due to Bochner, our representation immediately establishes the complete monotonicity of the horseshoe density and strong concavity of the corresponding penalty. Consequently, the equivalence between local linear approximation and expectation-maximization algorithms for finding the posterior mode under the horseshoe penalized regression is established. Further, the resultant estimate is shown to be sparse.</description><identifier>ISSN: 1070-9908</identifier><identifier>EISSN: 1558-2361</identifier><identifier>DOI: 10.1109/LSP.2022.3228491</identifier><identifier>CODEN: ISPLEM</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Bayesian sparse signal recovery ; Bernstein–Widder ; completely monotone function ; Concavity ; Convergence ; Density ; Estimation ; Linear approximation ; local linear approximation ; Mathematical models ; Mixtures ; Optimization ; Random variables ; Representations ; Signal reconstruction ; Tail</subject><ispartof>IEEE signal processing letters, 2022, Vol.29, p.2547-2551</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c333t-65edc0577ae34251f08aa2cbb8ab76851d1e3d50d4f29be65ea5f37f5a80f3183</citedby><cites>FETCH-LOGICAL-c333t-65edc0577ae34251f08aa2cbb8ab76851d1e3d50d4f29be65ea5f37f5a80f3183</cites><orcidid>0000-0003-0636-5273 ; 0000-0002-0973-2406</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9979805$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,786,790,4043,27956,27957,27958,55147</link.rule.ids></links><search><creatorcontrib>Sagar, Ksheera</creatorcontrib><creatorcontrib>Bhadra, Anindya</creatorcontrib><title>A Laplace Mixture Representation of the Horseshoe and Some Implications</title><title>IEEE signal processing letters</title><addtitle>LSP</addtitle><description>The horseshoe prior, defined as a half Cauchy scale mixture of normal, provides a state of the art approach to Bayesian sparse signal recovery. We provide a new representation of the horseshoe density as a scale mixture of the Laplace density, explicitly identifying the mixing measure. Using the celebrated Bernstein-Widder theorem and a result due to Bochner, our representation immediately establishes the complete monotonicity of the horseshoe density and strong concavity of the corresponding penalty. Consequently, the equivalence between local linear approximation and expectation-maximization algorithms for finding the posterior mode under the horseshoe penalized regression is established. Further, the resultant estimate is shown to be sparse.</description><subject>Algorithms</subject><subject>Bayesian sparse signal recovery</subject><subject>Bernstein–Widder</subject><subject>completely monotone function</subject><subject>Concavity</subject><subject>Convergence</subject><subject>Density</subject><subject>Estimation</subject><subject>Linear approximation</subject><subject>local linear approximation</subject><subject>Mathematical models</subject><subject>Mixtures</subject><subject>Optimization</subject><subject>Random variables</subject><subject>Representations</subject><subject>Signal reconstruction</subject><subject>Tail</subject><issn>1070-9908</issn><issn>1558-2361</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNo9kMFLwzAUxoMoOKd3wUvAc-dLsjTJcQzdhIri9BzS9oV1bE1NOtD_3s4NT-87_L7vwY-QWwYTxsA8FKu3CQfOJ4JzPTXsjIyYlDrjImfnQwYFmTGgL8lVShsA0EzLEVnMaOG6rauQvjTf_T4ifccuYsK2d30TWho87ddIlyEmTOuA1LU1XYUd0uddt22qPypdkwvvtglvTndMPp8eP-bLrHhdPM9nRVYJIfosl1hXIJVyKKZcMg_aOV6VpXalyrVkNUNRS6innpsSB9xJL5SXToMXTIsxuT_udjF87TH1dhP2sR1eWq6kYkpplQ8UHKkqhpQietvFZufij2VgD7rsoMsedNmTrqFyd6w0iPiPG6OMBil-Ae97ZcE</recordid><startdate>2022</startdate><enddate>2022</enddate><creator>Sagar, Ksheera</creator><creator>Bhadra, Anindya</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>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0003-0636-5273</orcidid><orcidid>https://orcid.org/0000-0002-0973-2406</orcidid></search><sort><creationdate>2022</creationdate><title>A Laplace Mixture Representation of the Horseshoe and Some Implications</title><author>Sagar, Ksheera ; Bhadra, Anindya</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c333t-65edc0577ae34251f08aa2cbb8ab76851d1e3d50d4f29be65ea5f37f5a80f3183</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Bayesian sparse signal recovery</topic><topic>Bernstein–Widder</topic><topic>completely monotone function</topic><topic>Concavity</topic><topic>Convergence</topic><topic>Density</topic><topic>Estimation</topic><topic>Linear approximation</topic><topic>local linear approximation</topic><topic>Mathematical models</topic><topic>Mixtures</topic><topic>Optimization</topic><topic>Random variables</topic><topic>Representations</topic><topic>Signal reconstruction</topic><topic>Tail</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sagar, Ksheera</creatorcontrib><creatorcontrib>Bhadra, Anindya</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE/IET Electronic Library</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology 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 signal processing letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sagar, Ksheera</au><au>Bhadra, Anindya</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Laplace Mixture Representation of the Horseshoe and Some Implications</atitle><jtitle>IEEE signal processing letters</jtitle><stitle>LSP</stitle><date>2022</date><risdate>2022</risdate><volume>29</volume><spage>2547</spage><epage>2551</epage><pages>2547-2551</pages><issn>1070-9908</issn><eissn>1558-2361</eissn><coden>ISPLEM</coden><abstract>The horseshoe prior, defined as a half Cauchy scale mixture of normal, provides a state of the art approach to Bayesian sparse signal recovery. We provide a new representation of the horseshoe density as a scale mixture of the Laplace density, explicitly identifying the mixing measure. Using the celebrated Bernstein-Widder theorem and a result due to Bochner, our representation immediately establishes the complete monotonicity of the horseshoe density and strong concavity of the corresponding penalty. Consequently, the equivalence between local linear approximation and expectation-maximization algorithms for finding the posterior mode under the horseshoe penalized regression is established. Further, the resultant estimate is shown to be sparse.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/LSP.2022.3228491</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0003-0636-5273</orcidid><orcidid>https://orcid.org/0000-0002-0973-2406</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1070-9908
ispartof IEEE signal processing letters, 2022, Vol.29, p.2547-2551
issn 1070-9908
1558-2361
language eng
recordid cdi_ieee_primary_9979805
source IEEE Electronic Library (IEL) Journals
subjects Algorithms
Bayesian sparse signal recovery
Bernstein–Widder
completely monotone function
Concavity
Convergence
Density
Estimation
Linear approximation
local linear approximation
Mathematical models
Mixtures
Optimization
Random variables
Representations
Signal reconstruction
Tail
title A Laplace Mixture Representation of the Horseshoe and Some Implications
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T21%3A29%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Laplace%20Mixture%20Representation%20of%20the%20Horseshoe%20and%20Some%20Implications&rft.jtitle=IEEE%20signal%20processing%20letters&rft.au=Sagar,%20Ksheera&rft.date=2022&rft.volume=29&rft.spage=2547&rft.epage=2551&rft.pages=2547-2551&rft.issn=1070-9908&rft.eissn=1558-2361&rft.coden=ISPLEM&rft_id=info:doi/10.1109/LSP.2022.3228491&rft_dat=%3Cproquest_ieee_%3E2757177876%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c333t-65edc0577ae34251f08aa2cbb8ab76851d1e3d50d4f29be65ea5f37f5a80f3183%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2757177876&rft_id=info:pmid/&rft_ieee_id=9979805&rfr_iscdi=true