{"title":"在贝叶斯优化中动态排除低保真数据,实现自主光束线对准","authors":"Megha R. Narayanan, Thomas W. Morris","doi":"arxiv-2408.06540","DOIUrl":null,"url":null,"abstract":"Aligning beamlines at synchrotron light sources is a high-dimensional,\nexpensive-to-sample optimization problem, as beams are focused using a series\nof dynamic optical components. Bayesian Optimization is an efficient machine\nlearning approach to finding global optima of beam quality, but the model can\neasily be impaired by faulty data points caused by the beam going off the edge\nof the sensor or by background noise. This study, conducted at the National\nSynchrotron Light Source II (NSLS-II) facility at Brookhaven National\nLaboratory (BNL), is an investigation of methods to identify untrustworthy\nreadings of beam quality and discourage the optimization model from seeking out\npoints likely to yield low-fidelity beams. The approaches explored include\ndynamic pruning using loss analysis of size and position models and a\nlengthscale-based genetic algorithm to determine which points to include in the\nmodel for optimal fit. Each method successfully classified high and low\nfidelity points. This research advances BNL's mission to tackle our nation's\nenergy challenges by providing scientists at all beamlines with access to\nhigher quality beams, and faster convergence to these optima for their\nexperiments.","PeriodicalId":501318,"journal":{"name":"arXiv - PHYS - Accelerator Physics","volume":"64 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dynamic Exclusion of Low-Fidelity Data in Bayesian Optimization for Autonomous Beamline Alignment\",\"authors\":\"Megha R. Narayanan, Thomas W. Morris\",\"doi\":\"arxiv-2408.06540\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Aligning beamlines at synchrotron light sources is a high-dimensional,\\nexpensive-to-sample optimization problem, as beams are focused using a series\\nof dynamic optical components. Bayesian Optimization is an efficient machine\\nlearning approach to finding global optima of beam quality, but the model can\\neasily be impaired by faulty data points caused by the beam going off the edge\\nof the sensor or by background noise. This study, conducted at the National\\nSynchrotron Light Source II (NSLS-II) facility at Brookhaven National\\nLaboratory (BNL), is an investigation of methods to identify untrustworthy\\nreadings of beam quality and discourage the optimization model from seeking out\\npoints likely to yield low-fidelity beams. The approaches explored include\\ndynamic pruning using loss analysis of size and position models and a\\nlengthscale-based genetic algorithm to determine which points to include in the\\nmodel for optimal fit. Each method successfully classified high and low\\nfidelity points. This research advances BNL's mission to tackle our nation's\\nenergy challenges by providing scientists at all beamlines with access to\\nhigher quality beams, and faster convergence to these optima for their\\nexperiments.\",\"PeriodicalId\":501318,\"journal\":{\"name\":\"arXiv - PHYS - Accelerator Physics\",\"volume\":\"64 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Accelerator Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.06540\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Accelerator Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.06540","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
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 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.