Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment

Aligning beamlines at synchrotron light sources is a high-dimensional, expensive-to-sample optimization problem, as beams are focused using a series of dynamic optical components. Bayesian Optimization is an efficient machine learning approach to finding global optima of beam quality, but the model...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Narayanan, Megha R, Morris, Thomas W
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 Narayanan, Megha R
Morris, Thomas W
description Aligning beamlines at synchrotron light sources is a high-dimensional, expensive-to-sample optimization problem, as beams are focused using a series of dynamic optical components. Bayesian Optimization is an efficient machine learning approach to finding global optima of beam quality, but the model can easily be impaired by faulty data points caused by the beam going off the edge of the sensor or by background noise. This study, conducted at the National Synchrotron Light Source II (NSLS-II) facility at Brookhaven National Laboratory (BNL), is an investigation of methods to identify untrustworthy readings of beam quality and discourage the optimization model from seeking out points likely to yield low-fidelity beams. The approaches explored include dynamic pruning using loss analysis of size and position models and a lengthscale-based genetic algorithm to determine which points to include in the model for optimal fit. Each method successfully classified high and low fidelity points. This research advances BNL's mission to tackle our nation's energy challenges by providing scientists at all beamlines with access to higher quality beams, and faster convergence to these optima for their experiments.
doi_str_mv 10.48550/arxiv.2408.06540
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2408_06540</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2408_06540</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2408_065403</originalsourceid><addsrcrecordid>eNqFzr0OgjAUQOEuDkZ9ACfvC4BVwbCCQBxMXNzJDRZzk_6Qtij16Y3E3eksZ_gYW-94nGRpyrdoR3rG-4RnMT-mCZ8zLINGRS1UYysHR0aD6eBiXlFNdyHJByjRI5CGAoNwhBquvSdFb_TfuzMW8sEbbZQZHBQClSQtIJf00Epov2SzDqUTq18XbFNXt9M5mjBNb0mhDc0X1Uyow__jA6lEQvo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment</title><source>arXiv.org</source><creator>Narayanan, Megha R ; Morris, Thomas W</creator><creatorcontrib>Narayanan, Megha R ; Morris, Thomas W</creatorcontrib><description>Aligning beamlines at synchrotron light sources is a high-dimensional, expensive-to-sample optimization problem, as beams are focused using a series of dynamic optical components. Bayesian Optimization is an efficient machine learning approach to finding global optima of beam quality, but the model can easily be impaired by faulty data points caused by the beam going off the edge of the sensor or by background noise. This study, conducted at the National Synchrotron Light Source II (NSLS-II) facility at Brookhaven National Laboratory (BNL), is an investigation of methods to identify untrustworthy readings of beam quality and discourage the optimization model from seeking out points likely to yield low-fidelity beams. The approaches explored include dynamic pruning using loss analysis of size and position models and a lengthscale-based genetic algorithm to determine which points to include in the model for optimal fit. Each method successfully classified high and low fidelity points. This research advances BNL's mission to tackle our nation's energy challenges by providing scientists at all beamlines with access to higher quality beams, and faster convergence to these optima for their experiments.</description><identifier>DOI: 10.48550/arxiv.2408.06540</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Physics - Accelerator Physics</subject><creationdate>2024-08</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</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/2408.06540$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2408.06540$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Narayanan, Megha R</creatorcontrib><creatorcontrib>Morris, Thomas W</creatorcontrib><title>Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment</title><description>Aligning beamlines at synchrotron light sources is a high-dimensional, expensive-to-sample optimization problem, as beams are focused using a series of dynamic optical components. Bayesian Optimization is an efficient machine learning approach to finding global optima of beam quality, but the model can easily be impaired by faulty data points caused by the beam going off the edge of the sensor or by background noise. This study, conducted at the National Synchrotron Light Source II (NSLS-II) facility at Brookhaven National Laboratory (BNL), is an investigation of methods to identify untrustworthy readings of beam quality and discourage the optimization model from seeking out points likely to yield low-fidelity beams. The approaches explored include dynamic pruning using loss analysis of size and position models and a lengthscale-based genetic algorithm to determine which points to include in the model for optimal fit. Each method successfully classified high and low fidelity points. This research advances BNL's mission to tackle our nation's energy challenges by providing scientists at all beamlines with access to higher quality beams, and faster convergence to these optima for their experiments.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Physics - Accelerator Physics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFzr0OgjAUQOEuDkZ9ACfvC4BVwbCCQBxMXNzJDRZzk_6Qtij16Y3E3eksZ_gYW-94nGRpyrdoR3rG-4RnMT-mCZ8zLINGRS1UYysHR0aD6eBiXlFNdyHJByjRI5CGAoNwhBquvSdFb_TfuzMW8sEbbZQZHBQClSQtIJf00Epov2SzDqUTq18XbFNXt9M5mjBNb0mhDc0X1Uyow__jA6lEQvo</recordid><startdate>20240812</startdate><enddate>20240812</enddate><creator>Narayanan, Megha R</creator><creator>Morris, Thomas W</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240812</creationdate><title>Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment</title><author>Narayanan, Megha R ; Morris, Thomas W</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2408_065403</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Physics - Accelerator Physics</topic><toplevel>online_resources</toplevel><creatorcontrib>Narayanan, Megha R</creatorcontrib><creatorcontrib>Morris, Thomas W</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Narayanan, Megha R</au><au>Morris, Thomas W</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment</atitle><date>2024-08-12</date><risdate>2024</risdate><abstract>Aligning beamlines at synchrotron light sources is a high-dimensional, expensive-to-sample optimization problem, as beams are focused using a series of dynamic optical components. Bayesian Optimization is an efficient machine learning approach to finding global optima of beam quality, but the model can easily be impaired by faulty data points caused by the beam going off the edge of the sensor or by background noise. This study, conducted at the National Synchrotron Light Source II (NSLS-II) facility at Brookhaven National Laboratory (BNL), is an investigation of methods to identify untrustworthy readings of beam quality and discourage the optimization model from seeking out points likely to yield low-fidelity beams. The approaches explored include dynamic pruning using loss analysis of size and position models and a lengthscale-based genetic algorithm to determine which points to include in the model for optimal fit. Each method successfully classified high and low fidelity points. This research advances BNL's mission to tackle our nation's energy challenges by providing scientists at all beamlines with access to higher quality beams, and faster convergence to these optima for their experiments.</abstract><doi>10.48550/arxiv.2408.06540</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2408.06540
ispartof
issn
language eng
recordid cdi_arxiv_primary_2408_06540
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Learning
Physics - Accelerator Physics
title Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T22%3A15%3A04IST&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=Dynamic%20Exclusion%20of%20Low-Fidelity%20Data%20in%20Bayesian%20Optimization%20for%20Autonomous%20Beamline%20Alignment&rft.au=Narayanan,%20Megha%20R&rft.date=2024-08-12&rft_id=info:doi/10.48550/arxiv.2408.06540&rft_dat=%3Carxiv_GOX%3E2408_06540%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