Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives
Although beam emittance is critical for the performance of high-brightness accelerators, optimization is often time limited as emittance calculations, commonly done via quadrupole scans, are typically slow. Such calculations are a type of multipoint query , i.e. each query requires multiple secondar...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2024-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad169f |
| _version_ | 1797359604204568576 |
|---|---|
| author | Sara Ayoub Miskovich Willie Neiswanger William Colocho Claudio Emma Jacqueline Garrahan Timothy Maxwell Christopher Mayes Stefano Ermon Auralee Edelen Daniel Ratner |
| author_facet | Sara Ayoub Miskovich Willie Neiswanger William Colocho Claudio Emma Jacqueline Garrahan Timothy Maxwell Christopher Mayes Stefano Ermon Auralee Edelen Daniel Ratner |
| author_sort | Sara Ayoub Miskovich |
| collection | DOAJ |
| description | Although beam emittance is critical for the performance of high-brightness accelerators, optimization is often time limited as emittance calculations, commonly done via quadrupole scans, are typically slow. Such calculations are a type of multipoint query , i.e. each query requires multiple secondary measurements. Traditional black-box optimizers such as Bayesian optimization are slow and inefficient when dealing with such objectives as they must acquire the full series of measurements, but return only the emittance, with each query. We propose a new information-theoretic algorithm, Multipoint-BAX , for black-box optimization on multipoint queries, which queries and models individual beam-size measurements using techniques from Bayesian Algorithm Execution (BAX). Our method avoids the slow multipoint query on the accelerator by acquiring points through a virtual objective , i.e. calculating the emittance objective from a fast learned model rather than directly from the accelerator. We use Multipoint-BAX to minimize emittance at the Linac Coherent Light Source (LCLS) and the Facility for Advanced Accelerator Experimental Tests II (FACET-II). In simulation, our method is 20× faster and more robust to noise compared to existing methods. In live tests, it matched the hand-tuned emittance at FACET-II and achieved a 24% lower emittance than hand-tuning at LCLS. Our method represents a conceptual shift for optimizing multipoint queries, and we anticipate that it can be readily adapted to similar problems in particle accelerators and other scientific instruments. |
| first_indexed | 2024-03-08T15:26:09Z |
| format | Article |
| id | doaj.art-16c8837fd6fe43389e1ad5c9584b3d4a |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-08T15:26:09Z |
| publishDate | 2024-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-16c8837fd6fe43389e1ad5c9584b3d4a2024-01-10T08:38:17ZengIOP PublishingMachine Learning: Science and Technology2632-21532024-01-015101500410.1088/2632-2153/ad169fMultipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectivesSara Ayoub Miskovich0https://orcid.org/0000-0002-3302-838XWillie Neiswanger1https://orcid.org/0000-0002-9619-5572William Colocho2Claudio Emma3Jacqueline Garrahan4Timothy Maxwell5Christopher Mayes6Stefano Ermon7Auralee Edelen8Daniel Ratner9SLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaDepartment of Computer Science, Stanford University , Stanford, CA, United States of AmericaSLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaSLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaSLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaSLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaSLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaDepartment of Computer Science, Stanford University , Stanford, CA, United States of AmericaSLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaSLAC National Accelerator Laboratory , Menlo Park, CA, United States of AmericaAlthough beam emittance is critical for the performance of high-brightness accelerators, optimization is often time limited as emittance calculations, commonly done via quadrupole scans, are typically slow. Such calculations are a type of multipoint query , i.e. each query requires multiple secondary measurements. Traditional black-box optimizers such as Bayesian optimization are slow and inefficient when dealing with such objectives as they must acquire the full series of measurements, but return only the emittance, with each query. We propose a new information-theoretic algorithm, Multipoint-BAX , for black-box optimization on multipoint queries, which queries and models individual beam-size measurements using techniques from Bayesian Algorithm Execution (BAX). Our method avoids the slow multipoint query on the accelerator by acquiring points through a virtual objective , i.e. calculating the emittance objective from a fast learned model rather than directly from the accelerator. We use Multipoint-BAX to minimize emittance at the Linac Coherent Light Source (LCLS) and the Facility for Advanced Accelerator Experimental Tests II (FACET-II). In simulation, our method is 20× faster and more robust to noise compared to existing methods. In live tests, it matched the hand-tuned emittance at FACET-II and achieved a 24% lower emittance than hand-tuning at LCLS. Our method represents a conceptual shift for optimizing multipoint queries, and we anticipate that it can be readily adapted to similar problems in particle accelerators and other scientific instruments.https://doi.org/10.1088/2632-2153/ad169fonline optimizationmultipoint optimizationparticle acceleratorx-ray free electron laserBayesian optimizationBayesian algorithm execution |
| spellingShingle | Sara Ayoub Miskovich Willie Neiswanger William Colocho Claudio Emma Jacqueline Garrahan Timothy Maxwell Christopher Mayes Stefano Ermon Auralee Edelen Daniel Ratner Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives Machine Learning: Science and Technology online optimization multipoint optimization particle accelerator x-ray free electron laser Bayesian optimization Bayesian algorithm execution |
| title | Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives |
| title_full | Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives |
| title_fullStr | Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives |
| title_full_unstemmed | Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives |
| title_short | Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives |
| title_sort | multipoint bax a new approach for efficiently tuning particle accelerator emittance via virtual objectives |
| topic | online optimization multipoint optimization particle accelerator x-ray free electron laser Bayesian optimization Bayesian algorithm execution |
| url | https://doi.org/10.1088/2632-2153/ad169f |
| work_keys_str_mv | AT saraayoubmiskovich multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT willieneiswanger multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT williamcolocho multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT claudioemma multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT jacquelinegarrahan multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT timothymaxwell multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT christophermayes multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT stefanoermon multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT auraleeedelen multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives AT danielratner multipointbaxanewapproachforefficientlytuningparticleacceleratoremittanceviavirtualobjectives |