{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400770,"version":"3.37.3"},"reference-count":63,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:00:00Z","timestamp":1704844800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:00:00Z","timestamp":1704844800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"crossref","award":["DE-AC02-76SF00515"],"award-info":[{"award-number":["DE-AC02-76SF00515"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>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<jats:italic>multipoint query<\/jats:italic>, 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,<jats:sc>Multipoint-BAX<\/jats:sc>, 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<jats:italic>virtual objective<\/jats:italic>, i.e. calculating the emittance objective from a fast learned model rather than directly from the accelerator. We use<jats:sc>Multipoint-BAX<\/jats:sc>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\u00d7 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.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad169f","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T22:24:58Z","timestamp":1702938298000},"page":"015004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3302-838X","authenticated-orcid":true,"given":"Sara","family":"Ayoub Miskovich","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9619-5572","authenticated-orcid":true,"given":"Willie","family":"Neiswanger","sequence":"additional","affiliation":[]},{"given":"William","family":"Colocho","sequence":"additional","affiliation":[]},{"given":"Claudio","family":"Emma","sequence":"additional","affiliation":[]},{"given":"Jacqueline","family":"Garrahan","sequence":"additional","affiliation":[]},{"given":"Timothy","family":"Maxwell","sequence":"additional","affiliation":[]},{"given":"Christopher","family":"Mayes","sequence":"additional","affiliation":[]},{"given":"Stefano","family":"Ermon","sequence":"additional","affiliation":[]},{"given":"Auralee","family":"Edelen","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Ratner","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,1,10]]},"reference":[{"key":"mlstad169fbib1","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1023\/A:1008306431147","article-title":"Efficient global optimization of expensive black-box functions","volume":"13","author":"Jones","year":"1998","journal-title":"J. Glob. Optim."},{"article-title":"A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning","year":"2010","author":"Brochu","key":"mlstad169fbib2"},{"key":"mlstad169fbib3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.18.084001","article-title":"Online optimization of storage ring nonlinear beam dynamics","volume":"18","author":"Huang","year":"2015","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstad169fbib4","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.21.104601","article-title":"Robust simplex algorithm for online optimization","volume":"21","author":"Huang","year":"2018","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad169fbib5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.16.102803","article-title":"Model-independent particle accelerator tuning","volume":"16","author":"Scheinker","year":"2013","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstad169fbib6","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1109\/TCST.2017.2664728","article-title":"Minimization of betatron oscillations of electron beam injected into a time-varying lattice via extremum seeking","volume":"26","author":"Scheinker","year":"2018","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"mlstad169fbib7","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.22.054601","article-title":"Online storage ring optimization using dimension-reduction and genetic algorithms","volume":"22","author":"Bergan","year":"2019","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad169fbib8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.22.082802","article-title":"Model-independent tuning for maximizing free electron laser pulse energy","volume":"22","author":"Scheinker","year":"2019","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad169fbib9","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1021\/acs.accounts.0c00713","article-title":"Black-box optimization for automated discovery","volume":"54","author":"Terayama","year":"2021","journal-title":"Acc. Chem. Res."},{"key":"mlstad169fbib10","first-page":"vol 32","article-title":"Offline contextual Bayesian optimization","author":"Char","year":"2019"},{"key":"mlstad169fbib11","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.md.2016.04.001","article-title":"Combo: an efficient Bayesian optimization library for materials science","volume":"4","author":"Ueno","year":"2016","journal-title":"Mater. Discovery"},{"key":"mlstad169fbib12","first-page":"pp 69","article-title":"A new method of locating the maximum point of an arbitrary multipeak curve in the presence of noise","author":"Kushner","year":"1963"},{"key":"mlstad169fbib13","first-page":"pp 400","article-title":"On Bayesian methods for seeking the extremum","author":"Mo\u010dkus","year":"1975","edition":"ed"},{"key":"mlstad169fbib14","first-page":"p WEOW055","article-title":"Bayesian optimization of FEL performance at LCLS","author":"McIntire","year":"2016"},{"article-title":"Adaptive and safe Bayesian optimization in high dimensions via one-dimensional subspaces","year":"2019","author":"Kirschner","key":"mlstad169fbib15"},{"key":"mlstad169fbib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.124801","article-title":"Bayesian optimization of a free-electron laser","volume":"124","author":"Duris","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstad169fbib17","doi-asserted-by":"publisher","first-page":"6355","DOI":"10.1038\/s41467-020-20245-6","article-title":"Automation and control of laser wakefield accelerators using Bayesian optimization","volume":"11","author":"Shalloo","year":"2020","journal-title":"Nat. Commun."},{"key":"mlstad169fbib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.24.062801","article-title":"Multiobjective Bayesian optimization for online accelerator tuning","volume":"24","author":"Roussel","year":"2021","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad169fbib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.2.013803","article-title":"Crystal structure prediction accelerated by Bayesian optimization","volume":"2","author":"Yamashita","year":"2018","journal-title":"Phys. Rev. Mater."},{"key":"mlstad169fbib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.25.044601","article-title":"Online Bayesian optimization for a recoil mass separator","volume":"25","author":"Miskovich","year":"2022","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad169fbib21","doi-asserted-by":"publisher","first-page":"104","DOI":"10.2514\/1.J052940","article-title":"Multimission aircraft fuel-burn minimization via multipoint aerostructural optimization","volume":"53","author":"Liem","year":"2015","journal-title":"AIAA J."},{"key":"mlstad169fbib22","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1093\/bioinformatics\/btx638","article-title":"Machine learning accelerates MD-based binding pose prediction between ligands and proteins","volume":"34","author":"Terayama","year":"2017","journal-title":"Bioinformatics"},{"key":"mlstad169fbib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.23.114201","article-title":"Longitudinal phase space reconstruction for a heavy ion accelerator","volume":"23","author":"Lauber","year":"2020","journal-title":"Phys. Rev. Accel. Beams"},{"volume":"vol 01","year":"2003","author":"Minty","key":"mlstad169fbib24"},{"key":"mlstad169fbib25","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1038\/nphoton.2010.176","article-title":"First lasing and operation of an \u00e5ngstrom-wavelength free-electron laser","volume":"4","author":"Emma","year":"2010","journal-title":"Nat. Photon."},{"key":"mlstad169fbib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.10.034801","article-title":"Review of x-ray free-electron laser theory","volume":"10","author":"Huang","year":"2007","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstad169fbib27","first-page":"1","article-title":"LCLS-ii high energy (LCLS-ii-HE): a transformative x-ray laser for science","author":"Schoenlein","year":"2016"},{"key":"mlstad169fbib28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.4.053501","article-title":"A low emittance, flat-beam electron source for linear colliders","volume":"4","author":"Brinkmann","year":"2001","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstad169fbib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.18.101002","article-title":"Optimizing integrated luminosity of future hadron colliders","volume":"18","author":"Benedikt","year":"2015","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstad169fbib30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.9.031001","article-title":"Photoinjector generation of a flat electron beam with transverse emittance ratio of 100","volume":"9","author":"Piot","year":"2006","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstad169fbib31","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.nima.2016.10.041","article-title":"Flat electron beam sources for DLA accelerators","volume":"865","author":"Ody","year":"2017","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"article-title":"Bayesian algorithm execution: estimating computable properties of black-box functions using mutual information","year":"2021","author":"Neiswanger","key":"mlstad169fbib32"},{"key":"mlstad169fbib33","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1093\/comjnl\/7.4.308","article-title":"A Simplex method for function minimization","volume":"7","author":"Nelder","year":"1965","journal-title":"Comput. J."},{"key":"mlstad169fbib34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.22.101301","article-title":"Facet-ii facility for advanced accelerator experimental tests","volume":"22","author":"Yakimenko","year":"2019","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad169fbib35","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/PLASMA.1991.695803","article-title":"Beam emittance measurement by the pepper-pot method","volume":"307","author":"Wang","year":"1991","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstad169fbib36","first-page":"757","article-title":"A high-resolution multi-slit phase space measurement technique for low-emittance beams","volume":"1507","author":"Thangaraj","year":"2012"},{"key":"mlstad169fbib37","doi-asserted-by":"crossref","DOI":"10.2172\/395453","article-title":"Emittance formula for slits and pepper-pot measurement","author":"Zhang","year":"1996"},{"first-page":"pp 213","year":"2006","author":"Strehl","key":"mlstad169fbib38"},{"key":"mlstad169fbib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.11.030703","article-title":"Commissioning the linac coherent light source injector","volume":"11","author":"Akre","year":"2008","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstad169fbib40","doi-asserted-by":"crossref","DOI":"10.2172\/2283895","article-title":"PyEmittance: a general python package for particle beam emittance measurements with adaptive quadrupole scans","author":"Miskovich","year":"2022"},{"key":"mlstad169fbib41","first-page":"vol 31","article-title":"GPyTorch: blackbox matrix-matrix Gaussian process inference with GPU acceleration","author":"Gardner","year":"2018"},{"key":"mlstad169fbib42","first-page":"3098","article-title":"Tuning hyperparameters without grad students: scalable and robust Bayesian optimisation with dragonfly","volume":"21","author":"Kandasamy","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad169fbib43","first-page":"1809","article-title":"Entropy search for information-efficient global optimization","volume":"13","author":"Hennig","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad169fbib44","first-page":"vol 27","article-title":"Predictive entropy search for efficient global optimization of black-box functions","author":"Miguel Hern\u00e1ndez-Lobato","year":"2014"},{"key":"mlstad169fbib45","first-page":"pp 3627","article-title":"Max-value entropy search for efficient Bayesian optimization","author":"Wang","year":"2017"},{"key":"mlstad169fbib46","first-page":"vol 32","article-title":"Max-value entropy search for multi-objective Bayesian optimization","author":"Belakaria","year":"2019"},{"key":"mlstad169fbib47","first-page":"pp 1799","article-title":"Multi-fidelity Bayesian optimisation with continuous approximations","author":"Kandasamy","year":"2017"},{"key":"mlstad169fbib48","first-page":"pp 10035","article-title":"Multi-fidelity multi-objective bayesian optimization: An output space entropy search approach","volume":"vol 34","author":"Belakaria","year":"2020"},{"key":"mlstad169fbib49","first-page":"p WEOY036","article-title":"Progress in automatic software-based optimization of accelerator performance","author":"Tomin","year":"2016"},{"key":"mlstad169fbib50","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.24.072802","article-title":"Physics model-informed Gaussian process for online optimization of particle accelerators","volume":"24","author":"Adi Hanuka","year":"2021","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad169fbib51","doi-asserted-by":"publisher","first-page":"5612","DOI":"10.1038\/s41467-021-25757-3","article-title":"Turn-key constrained parameter space exploration for particle accelerators using Bayesian active learning","volume":"12","author":"Roussel","year":"2021","journal-title":"Nat. Commun."},{"article-title":"Neural network prior mean for particle accelerator injector tuning","year":"2022","author":"Xu","key":"mlstad169fbib52"},{"article-title":"pyepics\/pyepics (3.4.0)","year":"2019","author":"Newville","key":"mlstad169fbib53"},{"key":"mlstad169fbib54","first-page":"6","article-title":"Operational performance of LCLS beam instrumentation","author":"(Livermore SLAC, LLNL)","year":"2010"},{"article-title":"Measurements of the transverse emittance at the VUV-FEL","year":"2005","author":"Loehl","key":"mlstad169fbib55"},{"key":"mlstad169fbib56","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1109\/PAC.1995.504603","article-title":"Design optimization for an x-ray free electron laser driven by SLAC LINAC","volume":"950501","author":"Xie","year":"1996","journal-title":"Conf. Proc. C"},{"key":"mlstad169fbib57","article-title":"FEL gain length and taper measurements at LCLS","volume":"vol 7","author":"Ratner","year":"2010"},{"article-title":"Enhancing explainability of hyperparameter optimization via Bayesian algorithm execution","year":"2022","author":"Moosbauer","key":"mlstad169fbib58"},{"article-title":"An experimental design perspective on model-based reinforcement learning","year":"2021","author":"Mehta","key":"mlstad169fbib59"},{"key":"mlstad169fbib60","first-page":"pp 3222","article-title":"Myopic posterior sampling for adaptive goal oriented design of experiments","author":"Kandasamy","year":"2019"},{"key":"mlstad169fbib61","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.9.044204","article-title":"Three-dimensional quasistatic model for high brightness beam dynamics simulation","volume":"9","author":"Qiang","year":"2006","journal-title":"Phys. Rev. ST Accel. Beams"},{"article-title":"Bayesian optimization: open source constrained global optimization tool for Python (version 1.1)","year":"2014","author":"Nogueira","key":"mlstad169fbib62"},{"key":"mlstad169fbib63","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in python, (version 1.7.3)","volume":"17","author":"SciPy 1.0 Contributors","year":"2020","journal-title":"Nat. Methods"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T08:16:47Z","timestamp":1730881007000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad169f"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,10]]},"references-count":63,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1,10]]},"published-print":{"date-parts":[[2024,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad169f","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2024,1,10]]},"assertion":[{"value":"Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-08-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-12-18","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-10","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}