Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty

When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algor...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	van der Herten, Joachim, Couckuyt, Ivo, Deschrijver, Dirk, Dhaene, Tom
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Statistics - Machine Learning
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	van der Herten, Joachim Couckuyt, Ivo Deschrijver, Dirk Dhaene, Tom
description	When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically puts more emphasis on exploration to provide more information to the models.
doi_str_mv	10.48550/arxiv.1608.05225
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1608_05225</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1608_05225</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-457bb30053e405bc0018795809551814fc9166d2fc5059e78b8c64e58c4a7ccc3</originalsourceid><addsrcrecordid>eNotz8FOwzAQBFBfOKDCB3DCP5CwTryOc4xKC0gRvZRz5GwdsNQ6keOU9O8hhdNIo9FIj7EHAanUiPBkwuzOqVCgU8Asw1tGFUV3try2JnjnP3nXB14NQ-hndzLR9Z73Hd_Mg_XjsttOnpZ25N8ufvH3PpzMkT-7MQbXTtEe-G6KwxT5hycbonE-Xu7YTWeOo73_zxXbbzf79WtS717e1lWdGFVgIrFo2xwAcysBWwIQuihRQ4kotJAdlUKpQ9YRApa20K0mJS1qkqYgonzFHv9ur8pmCL-AcGkWbXPV5j9SWFC0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty</title><source>arXiv.org</source><creator>van der Herten, Joachim ; Couckuyt, Ivo ; Deschrijver, Dirk ; Dhaene, Tom</creator><creatorcontrib>van der Herten, Joachim ; Couckuyt, Ivo ; Deschrijver, Dirk ; Dhaene, Tom</creatorcontrib><description>When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically puts more emphasis on exploration to provide more information to the models.</description><identifier>DOI: 10.48550/arxiv.1608.05225</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2016-08</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1608.05225$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1608.05225$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>van der Herten, Joachim</creatorcontrib><creatorcontrib>Couckuyt, Ivo</creatorcontrib><creatorcontrib>Deschrijver, Dirk</creatorcontrib><creatorcontrib>Dhaene, Tom</creatorcontrib><title>Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty</title><description>When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically puts more emphasis on exploration to provide more information to the models.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8FOwzAQBFBfOKDCB3DCP5CwTryOc4xKC0gRvZRz5GwdsNQ6keOU9O8hhdNIo9FIj7EHAanUiPBkwuzOqVCgU8Asw1tGFUV3try2JnjnP3nXB14NQ-hndzLR9Z73Hd_Mg_XjsttOnpZ25N8ufvH3PpzMkT-7MQbXTtEe-G6KwxT5hycbonE-Xu7YTWeOo73_zxXbbzf79WtS717e1lWdGFVgIrFo2xwAcysBWwIQuihRQ4kotJAdlUKpQ9YRApa20K0mJS1qkqYgonzFHv9ur8pmCL-AcGkWbXPV5j9SWFC0</recordid><startdate>20160818</startdate><enddate>20160818</enddate><creator>van der Herten, Joachim</creator><creator>Couckuyt, Ivo</creator><creator>Deschrijver, Dirk</creator><creator>Dhaene, Tom</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20160818</creationdate><title>Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty</title><author>van der Herten, Joachim ; Couckuyt, Ivo ; Deschrijver, Dirk ; Dhaene, Tom</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-457bb30053e405bc0018795809551814fc9166d2fc5059e78b8c64e58c4a7ccc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>van der Herten, Joachim</creatorcontrib><creatorcontrib>Couckuyt, Ivo</creatorcontrib><creatorcontrib>Deschrijver, Dirk</creatorcontrib><creatorcontrib>Dhaene, Tom</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>van der Herten, Joachim</au><au>Couckuyt, Ivo</au><au>Deschrijver, Dirk</au><au>Dhaene, Tom</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty</atitle><date>2016-08-18</date><risdate>2016</risdate><abstract>When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically puts more emphasis on exploration to provide more information to the models.</abstract><doi>10.48550/arxiv.1608.05225</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.1608.05225
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_1608_05225
source	arXiv.org
subjects	Computer Science - Learning Statistics - Machine Learning
title	Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T05%3A08%3A02IST&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=Active%20Learning%20for%20Approximation%20of%20Expensive%20Functions%20with%20Normal%20Distributed%20Output%20Uncertainty&rft.au=van%20der%20Herten,%20Joachim&rft.date=2016-08-18&rft_id=info:doi/10.48550/arxiv.1608.05225&rft_dat=%3Carxiv_GOX%3E1608_05225%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