{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T00:44:06Z","timestamp":1784940246105,"version":"3.55.0"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T00:00:00Z","timestamp":1619395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006041","name":"Innovate UK","doi-asserted-by":"crossref","award":["104400"],"award-info":[{"award-number":["104400"]}],"id":[{"id":"10.13039\/501100006041","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2021,6,28]]},"abstract":"<jats:p>The performance of acquisition functions for Bayesian optimisation to locate the global optimum of continuous functions is investigated in terms of the Pareto front between exploration and exploitation. We show that Expected Improvement (EI) and the Upper Confidence Bound (UCB) always select solutions to be expensively evaluated on the Pareto front, but Probability of Improvement is not guaranteed to do so and Weighted Expected Improvement does so only for a restricted range of weights.<\/jats:p>\n          <jats:p>\n            We introduce two novel\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            -greedy acquisition functions. Extensive empirical evaluation of these together with random search, purely exploratory, and purely exploitative search on 10 benchmark problems in 1 to 10 dimensions shows that\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            -greedy algorithms are generally at least as effective as conventional acquisition functions (e.g., EI and UCB), particularly with a limited budget. In higher dimensions,\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            -greedy approaches are shown to have improved performance over conventional approaches. These results are borne out on a real-world computational fluid dynamics optimisation problem and a robotics active learning problem. Our analysis and experiments suggest that the most effective strategy, particularly in higher dimensions, is to be mostly greedy, occasionally selecting a random exploratory solution.\n          <\/jats:p>","DOI":"10.1145\/3425501","type":"journal-article","created":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T15:45:41Z","timestamp":1619451941000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":98,"title":["Greed Is Good: Exploration and Exploitation Trade-offs in Bayesian Optimisation"],"prefix":"10.1145","volume":"1","author":[{"given":"George","family":"De Ath","sequence":"first","affiliation":[{"name":"University of Exeter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard M.","family":"Everson","sequence":"additional","affiliation":[{"name":"University of Exeter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alma A. M.","family":"Rahat","sequence":"additional","affiliation":[{"name":"Swansea University, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan E.","family":"Fieldsend","sequence":"additional","affiliation":[{"name":"University of Exeter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,4,26]]},"reference":[{"key":"e_1_2_2_1_1","first-page":"21524","article-title":"BoTorch: A framework for efficient Monte-Carlo Bayesian optimization","volume":"33","author":"Balandat Maximilian","year":"2020","unstructured":"Maximilian Balandat, Brian Karrer, Daniel Jiang, Samuel Daulton, Ben Letham, Andrew G. Wilson, and Eytan Bakshy. 2020. BoTorch: A framework for efficient Monte-Carlo Bayesian optimization. Advances in Neural Information Processing Systems 33 (2020), 21524--21538.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_2_1","volume-title":"How to create generalizable results","author":"Bartz-Beielstein Thomas","unstructured":"Thomas Bartz-Beielstein. 2015. How to create generalizable results. In Springer Handbook of Computational Intelligence, Janusz Kacprzyk and Witold Pedrycz (Eds.). Springer, Berlin, 1127--1142."},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09584-4_17"},{"key":"e_1_2_2_4_1","volume-title":"Convergence rates of efficient global optimization algorithms. J. Mach. Learn. Res. 12 (Oct","author":"Bull Adam D.","year":"2011","unstructured":"Adam D. Bull. 2011. Convergence rates of efficient global optimization algorithms. J. Mach. Learn. Res. 12 (Oct. 2011), 2879--2904."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1137\/0916069"},{"key":"e_1_2_2_6_1","volume-title":"Proceedings of the Conference on Parallel Problem Solving from Nature (PPSN\u201918)","author":"Daniels Steven J.","unstructured":"Steven J. Daniels, Alma A. M. Rahat, Richard M. Everson, Gavin R. Tabor, and Jonathan E. Fieldsend. 2018. A suite of computationally expensive shape optimisation problems using computational fluid dynamics. In Proceedings of the Conference on Parallel Problem Solving from Nature (PPSN\u201918). Springer, 296--307."},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618562.2019.1683165"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-014-0210-2"},{"key":"e_1_2_2_10_1","volume-title":"Keane","author":"Forrester Alexander I. J.","year":"2008","unstructured":"Alexander I. J. Forrester, Andras Sobester, and Andy J. Keane. 2008. Engineering Design via Surrogate Modelling\u2014A Practical Guide. Wiley."},{"key":"e_1_2_2_11_1","volume-title":"Proceedings of the 19th International Conference on Artificial Intelligence and Statistics","volume":"51","author":"Gonz\u00e1lez Javier","year":"2016","unstructured":"Javier Gonz\u00e1lez, Zhenwen Dai, Philipp Hennig, and Neil Lawrence. 2016a. Batch Bayesian optimization via local penalization. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, Vol. 51. PMLR, 648--657."},{"key":"e_1_2_2_12_1","volume-title":"Proceedings of the 19th International Conference on Artificial Intelligence and Statistics","volume":"51","author":"Gonz\u00e1lez Javier","year":"2016","unstructured":"Javier Gonz\u00e1lez, Michael Osborne, and Neil Lawrence. 2016b. GLASSES: Relieving the myopia of Bayesian optimisation. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, Vol. 51. PMLR, 790--799."},{"key":"e_1_2_2_13_1","unstructured":"GPy. 2012. GPy: A Gaussian process framework in Python. Retrieved from http:\/\/github.com\/SheffieldML\/GPy."},{"key":"e_1_2_2_14_1","unstructured":"GPyOpt. 2016. GPyOpt: A Bayesian Optimization framework in Python. Retrieved from http:\/\/github.com\/SheffieldML\/GPyOpt."},{"key":"e_1_2_2_15_1","volume-title":"Wilke","author":"Grobler Carla","year":"2017","unstructured":"Carla Grobler, Schalk Kok, and Daniel N. Wilke. 2017. Simple intuitive multi-objective ParalLElization of efficient global optimization: SIMPLE-EGO. In Proceedings of the World Congress of Structural and Multidisciplinary Optimisation. Springer, 205--220."},{"key":"e_1_2_2_16_1","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm Sture","year":"1979","unstructured":"Sture Holm. 1979. A simple sequentially rejective multiple test procedure. Scand. J. Stat. 6, 2 (1979), 65--70.","journal-title":"Scand. J. Stat."},{"key":"e_1_2_2_17_1","volume-title":"International Conference on Machine Learning. PMLR, 4794--4803","author":"Jiang Shali","year":"2020","unstructured":"Shali Jiang, Henry Chai, Javier Gonzalez, and Roman Garnett. 2020. BINOCULARS for efficient, nonmyopic sequential experimental design. In International Conference on Machine Learning. PMLR, 4794--4803."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012771025575"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653121"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2000.10485979"},{"key":"e_1_2_2_25_1","volume-title":"et\u00a0al","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, et\u00a0al. 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529--533."},{"key":"e_1_2_2_26_1","first-page":"117","article-title":"The application of Bayesian methods for seeking the extremum","volume":"2","author":"Mo\u010dkus Jonas","year":"1978","unstructured":"Jonas Mo\u010dkus, Vytautas Tie\u0161is, and Antanas \u017dilinskas. 1978. The application of Bayesian methods for seeking the extremum. Towards Global Optimiz. 2, 1 (1978), 117--129.","journal-title":"Towards Global Optimiz."},{"key":"e_1_2_2_28_1","volume-title":"Williams","author":"Rasmussen Carl Edward","year":"2006","unstructured":"Carl Edward Rasmussen and Christopher K. I. Williams. 2006. Gaussian Processes for Machine Learning. The MIT Press, Boston, MA."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_2_2_31_1","volume-title":"Adams","author":"Snoek Jasper","year":"2012","unstructured":"Jasper Snoek, Hugo Larochelle, and Ryan P. Adams. 2012. Practical Bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems. Curran Associates, 2951--2959."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-004-6733-1"},{"key":"e_1_2_2_33_1","volume-title":"Proceedings of the 27th International Conference on Machine Learning. Omnipress, 1015--1022","author":"Srinivas Niranjan","year":"2010","unstructured":"Niranjan Srinivas, Andreas Krause, Sham Kakade, and Matthias Seeger. 2010. Gaussian process optimization in the bandit setting: No regret and experimental design. In Proceedings of the 27th International Conference on Machine Learning. Omnipress, 1015--1022."},{"key":"e_1_2_2_34_1","volume-title":"Barto","author":"Sutton Richard S.","year":"1998","unstructured":"Richard S. Sutton and Andrew G. Barto. 1998. Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16111-7_23"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00061"},{"key":"e_1_2_2_38_1","volume-title":"Emmerich","author":"Wang Hao","year":"2015","unstructured":"Hao Wang, Thomas B\u00e4ck, and Michael T. M. Emmerich. 2015. Multi-point efficient global optimization using niching evolution strategy. In EVOLVE\u2014A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation VI. Springer, 146--162."},{"key":"e_1_2_2_39_1","unstructured":"Ziyu Wang and Nando de Freitas. 2014. Theoretical analysis of Bayesian optimisation with unknown Gaussian process hyper-parameters. Retrieved from https:\/\/arXiv:1406.7758."},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594027"},{"key":"e_1_2_2_41_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning. PMLR, 3627--3635","author":"Wang Zi","year":"2017","unstructured":"Zi Wang and Stefanie Jegelka. 2017. Max-value entropy search for efficient Bayesian optimization. In Proceedings of the 34th International Conference on Machine Learning. PMLR, 3627--3635."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-018-0622-5"}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3425501","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3425501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:55Z","timestamp":1750195915000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3425501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,26]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,6,28]]}},"alternative-id":["10.1145\/3425501"],"URL":"https:\/\/doi.org\/10.1145\/3425501","relation":{},"ISSN":["2688-299X","2688-3007"],"issn-type":[{"value":"2688-299X","type":"print"},{"value":"2688-3007","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,26]]},"assertion":[{"value":"2019-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}