Non-asymptotic error bounds for scaled underdamped Langevin MCMC
Recent works have derived non-asymptotic upper bounds for convergence of underdamped Langevin MCMC. We revisit these bound and consider introducing scaling terms in the underlying underdamped Langevin equation. In particular, we provide conditions under which an appropriate scaling allows to improve...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Zajic, Tim |
| description | Recent works have derived non-asymptotic upper bounds for convergence of
underdamped Langevin MCMC. We revisit these bound and consider introducing
scaling terms in the underlying underdamped Langevin equation. In particular,
we provide conditions under which an appropriate scaling allows to improve the
error bounds in terms of the condition number of the underlying density of
interest. |
| doi_str_mv | 10.48550/arxiv.1912.03154 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1912_03154</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1912_03154</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-a82e047fca72b012b10fd3ab162afd5c9a84e1c9086e3c5de8b66cc1318664203</originalsourceid><addsrcrecordid>eNotj8lOwzAURb1hgQofwAr_QIKfpzg7UMQkpWXTffRsP6NIzSCnVPTvCYXVPXdzpMPYHYhSO2PEA-bv_lRCDbIUCoy-Zo-7aSxwOQ_zcTr2gVPOU-Z--hrjwtOKS8ADRb5-yhGHeeUWx0869SPfNtvmhl0lPCx0-78btn953jdvRfvx-t48tQXaShfoJAldpYCV9AKkB5GiQg9WYoom1Og0QaiFs6SCieS8tSGAAmetlkJt2P2f9pLQzbkfMJ-735TukqJ-AB1CQ58</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Non-asymptotic error bounds for scaled underdamped Langevin MCMC</title><source>arXiv.org</source><creator>Zajic, Tim</creator><creatorcontrib>Zajic, Tim</creatorcontrib><description>Recent works have derived non-asymptotic upper bounds for convergence of
underdamped Langevin MCMC. We revisit these bound and consider introducing
scaling terms in the underlying underdamped Langevin equation. In particular,
we provide conditions under which an appropriate scaling allows to improve the
error bounds in terms of the condition number of the underlying density of
interest.</description><identifier>DOI: 10.48550/arxiv.1912.03154</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2019-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1912.03154$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1912.03154$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zajic, Tim</creatorcontrib><title>Non-asymptotic error bounds for scaled underdamped Langevin MCMC</title><description>Recent works have derived non-asymptotic upper bounds for convergence of
underdamped Langevin MCMC. We revisit these bound and consider introducing
scaling terms in the underlying underdamped Langevin equation. In particular,
we provide conditions under which an appropriate scaling allows to improve the
error bounds in terms of the condition number of the underlying density of
interest.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8lOwzAURb1hgQofwAr_QIKfpzg7UMQkpWXTffRsP6NIzSCnVPTvCYXVPXdzpMPYHYhSO2PEA-bv_lRCDbIUCoy-Zo-7aSxwOQ_zcTr2gVPOU-Z--hrjwtOKS8ADRb5-yhGHeeUWx0869SPfNtvmhl0lPCx0-78btn953jdvRfvx-t48tQXaShfoJAldpYCV9AKkB5GiQg9WYoom1Og0QaiFs6SCieS8tSGAAmetlkJt2P2f9pLQzbkfMJ-735TukqJ-AB1CQ58</recordid><startdate>20191206</startdate><enddate>20191206</enddate><creator>Zajic, Tim</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20191206</creationdate><title>Non-asymptotic error bounds for scaled underdamped Langevin MCMC</title><author>Zajic, Tim</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-a82e047fca72b012b10fd3ab162afd5c9a84e1c9086e3c5de8b66cc1318664203</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Zajic, Tim</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zajic, Tim</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Non-asymptotic error bounds for scaled underdamped Langevin MCMC</atitle><date>2019-12-06</date><risdate>2019</risdate><abstract>Recent works have derived non-asymptotic upper bounds for convergence of
underdamped Langevin MCMC. We revisit these bound and consider introducing
scaling terms in the underlying underdamped Langevin equation. In particular,
we provide conditions under which an appropriate scaling allows to improve the
error bounds in terms of the condition number of the underlying density of
interest.</abstract><doi>10.48550/arxiv.1912.03154</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1912.03154 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1912_03154 |
| source | arXiv.org |
| subjects | Computer Science - Learning Statistics - Machine Learning |
| title | Non-asymptotic error bounds for scaled underdamped Langevin MCMC |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T03%3A06%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Non-asymptotic%20error%20bounds%20for%20scaled%20underdamped%20Langevin%20MCMC&rft.au=Zajic,%20Tim&rft.date=2019-12-06&rft_id=info:doi/10.48550/arxiv.1912.03154&rft_dat=%3Carxiv_GOX%3E1912_03154%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |