{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T06:01:26Z","timestamp":1774332086863,"version":"3.50.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Inferring optimal solutions from limited data is considered the ultimate goal in scientific discovery. Artificial intelligence offers a promising avenue to greatly accelerate this process. Existing methods often depend on large datasets, strong assumptions about objective functions, and classic machine learning techniques, restricting their effectiveness to low-dimensional or data-rich problems. Here we introduce an optimization pipeline that can effectively tackle complex, high-dimensional problems with limited data. This approach utilizes a deep neural surrogate to iteratively find optimal solutions and introduces additional mechanisms to avoid local optima, thereby minimizing the required samples. Our method finds superior solutions in problems with up to 2,000 dimensions, whereas existing approaches are confined to 100 dimensions and need considerably more data. It excels across varied real-world systems, outperforming current algorithms and enabling efficient knowledge discovery. Although focused on scientific problems, its benefits extend to numerous quantitative fields, paving the way for advanced self-driving laboratories.<\/jats:p>","DOI":"10.1038\/s43588-025-00858-x","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T09:04:09Z","timestamp":1756112649000},"page":"801-812","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep active optimization for complex systems"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1965-2298","authenticated-orcid":false,"given":"Ye","family":"Wei","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0416-9076","authenticated-orcid":false,"given":"Bo","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Ruiwen","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Yangtao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Bauer","sequence":"additional","affiliation":[]},{"given":"Po-Yen","family":"Tung","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0194-6124","authenticated-orcid":false,"given":"Dierk","family":"Raabe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"key":"858_CR1","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1038\/s41573-023-00672-y","volume":"22","author":"G Li","year":"2023","unstructured":"Li, G., Hilgenfeld, R., Whitley, R. & Clercq, E. D. Therapeutic strategies for COVID-19: progress and lessons learned. Nat. Rev. Drug Discov. 22, 449\u2013475 (2023).","journal-title":"Nat. Rev. Drug Discov."},{"key":"858_CR2","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1613\/jair.295","volume":"4","author":"DA Cohn","year":"1996","unstructured":"Cohn, D. A., Ghahramani, Z. & Jordan, M. I. Active learning with statistical models. J. Artif. Intell. Res. 4, 129\u2013145 (1996).","journal-title":"J. Artif. Intell. Res."},{"key":"858_CR3","unstructured":"Settles, B. From theories to queries: active learning in practice. In Active Learning and Experimental Design Workshop in Conjunction with AISTATS 2010 (eds Guyon, I. et al.) 1\u201318 (PMLR, 2011)."},{"key":"858_CR4","first-page":"45","volume":"2","author":"S Tong","year":"2001","unstructured":"Tong, S. & Koller, D. Support vector machine active learning with applications to text classification. J. Mach. Learn. Res. 2, 45\u201366 (2001).","journal-title":"J. Mach. Learn. Res."},{"key":"858_CR5","doi-asserted-by":"publisher","first-page":"eaax1566","DOI":"10.1126\/science.aax1566","volume":"365","author":"CW Coley","year":"2019","unstructured":"Coley, C. W. et al. A robotic platform for flow synthesis of organic compounds informed by ai planning. Science 365, eaax1566 (2019).","journal-title":"Science"},{"key":"858_CR6","doi-asserted-by":"publisher","first-page":"2454","DOI":"10.1021\/acs.accounts.2c00220","volume":"55","author":"M Seifrid","year":"2022","unstructured":"Seifrid, M. et al. Autonomous chemical experiments: challenges and perspectives on establishing a self-driving lab. Acc. Chem. Res. 55, 2454\u20132466 (2022).","journal-title":"Acc. Chem. Res."},{"key":"858_CR7","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1126\/science.adc8743","volume":"378","author":"NH Angello","year":"2022","unstructured":"Angello, N. H. et al. Closed-loop optimization of general reaction conditions for heteroaryl Suzuki\u2013Miyaura coupling. Science 378, 399\u2013405 (2022).","journal-title":"Science"},{"key":"858_CR8","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1038\/s41557-022-01016-w","volume":"14","author":"JS Manzano","year":"2022","unstructured":"Manzano, J. S. et al. An autonomous portable platform for universal chemical synthesis. Nat. Chem. 14, 1311\u20131318 (2022).","journal-title":"Nat. Chem."},{"key":"858_CR9","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41586-023-06735-9","volume":"624","author":"A Merchant","year":"2023","unstructured":"Merchant, A. et al. Scaling deep learning for materials discovery. Nature 624, 80\u201385 (2023).","journal-title":"Nature"},{"key":"858_CR10","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1162\/evco_a_00298","volume":"30","author":"D Brockhoff","year":"2022","unstructured":"Brockhoff, D., Auger, A., Hansen, N. & Tusar, T. Using well-understood single-objective functions in multiobjective black-box optimization test suites. Evol. Comput. 30, 165\u2013193 (2022).","journal-title":"Evol. Comput."},{"key":"858_CR11","doi-asserted-by":"crossref","unstructured":"Conn, A. R., Scheinberg, K. & Vicente, L. N. Introduction to Derivative-Free Optimization (Society for Industrial and Applied Mathematics, 2009).","DOI":"10.1137\/1.9780898718768"},{"key":"858_CR12","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1017\/S0962492919000060","volume":"28","author":"J Larson","year":"2019","unstructured":"Larson, J., Menickelly, M. & Wild, S. M. Derivative-free optimization methods. Acta Numer. 28, 287\u2013404 (2019).","journal-title":"Acta Numer."},{"key":"858_CR13","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","volume":"104","author":"B Shahriari","year":"2016","unstructured":"Shahriari, B., Swersky, K., Wang, Z., Adams, R. P. & de Freitas, N. Taking the human out of the loop: a review of Bayesian optimization. Proc. IEEE 104, 148\u2013175 (2016).","journal-title":"Proc. IEEE"},{"key":"858_CR14","first-page":"1655","volume":"12","author":"S Bubeck","year":"2011","unstructured":"Bubeck, S., Munos, R., Stoltz, G. & Szepesv\u00e1ri, C. X-armed bandits. J. Mach. Learn. Res. 12, 1655\u20131695 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"858_CR15","unstructured":"Springenberg, J. T., Klein, A., Falkner, S. & Hutter, F. Bayesian optimization with robust Bayesian neural networks. In Advances in Neural Information Processing Systems (eds Lee, D. et al.) (Curran Associates, 2016)."},{"key":"858_CR16","unstructured":"Bishop, C. M. Pattern Recognition and Machine Learning (Springer, 2006)."},{"key":"858_CR17","unstructured":"Snoek, J., Larochelle, H. & Adams, R. P. Practical Bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems (eds Pereira, F. et al.) (Curran Associates, 2012)."},{"key":"858_CR18","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"858_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio, Y. Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1\u2013127 (2009).","journal-title":"Found. Trends Mach. Learn."},{"key":"858_CR20","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (eds Pereira, F. et al.) (Curran Associates, 2012)."},{"key":"858_CR21","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1002\/rob.21918","volume":"37","author":"S Grigorescu","year":"2019","unstructured":"Grigorescu, S., Trasnea, B., Cocias, T. & Macesanu, G. A survey of deep learning techniques for autonomous driving. J. Field Robot. 37, 362\u2013386 (2019).","journal-title":"J. Field Robot."},{"key":"858_CR22","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D. et al. Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016).","journal-title":"Nature"},{"key":"858_CR23","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D. et al. A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362, 1140\u20131144 (2018).","journal-title":"Science"},{"key":"858_CR24","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O. et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019).","journal-title":"Nature"},{"key":"858_CR25","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P. & Levine, S. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. Proc. 35th International Conference on Machine Learning (eds Dy, J. & Krause, A.) 1861\u20131870 (PMLR, 2018)."},{"key":"858_CR26","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1038\/s43588-023-00406-5","volume":"3","author":"M Kulichenko","year":"2023","unstructured":"Kulichenko, M. et al. Uncertainty-driven dynamics for active learning of interatomic potentials. Nat. Comput. Sci. 3, 230\u2013239 (2023).","journal-title":"Nat. Comput. Sci."},{"key":"858_CR27","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P. & Fischer, P. Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47, 235\u2013256 (2002).","journal-title":"Mach. Learn."},{"key":"858_CR28","first-page":"397","volume":"3","author":"P Auer","year":"2002","unstructured":"Auer, P. Using confidence bounds for exploitation-exploration trade-offs. J. Mach. Learn. Res. 3, 397\u2013422 (2002).","journal-title":"J. Mach. Learn. Res."},{"key":"858_CR29","doi-asserted-by":"crossref","unstructured":"Kocsis, L. & Szepesv\u00e1ri, C. Bandit based Monte-Carlo planning. In Proc. 17th European Conference on Machine Learning (eds F\u00fcrnkranz, J. et al.) 282\u2013293 (Springer, 2006).","DOI":"10.1007\/11871842_29"},{"key":"858_CR30","first-page":"9916","volume":"34","author":"B Kim","year":"2020","unstructured":"Kim, B., Lee, K., Lim, S., Kaelbling, L. & Lozano-Perez, T. Monte Carlo tree search in continuous spaces using voronoi optimistic optimization with regret bounds. Proc. AAAI Conf. Artif. Intell. 34, 9916\u20139924 (2020).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"858_CR31","unstructured":"Eriksson, D., Pearce, M., Gardner, J. R., Turner, R. & Poloczek, M. Scalable global optimization via local Bayesian optimization. In Advances in Neural Information Processing Systems (eds Wallach, H. et al.) (Curran Associates, 2019)."},{"key":"858_CR32","unstructured":"Wang, L., Fonseca, R. & Tian, Y. Learning search space partition for black-box optimization using Monte Carlo tree search. In Advances in Neural Information Processing Systems (eds Larochelle, H. et al.) 19511\u201319522 (Curran Associates, 2020)."},{"key":"858_CR33","unstructured":"Mcinnes, L., Healy, J. & Melville, J. UMAP: uniform manifold approximation and projection for dimension reduction. Preprint at https:\/\/arxiv.org\/abs\/1802.03426 (2020)."},{"key":"858_CR34","unstructured":"Zoph, B. & Le, Q. V. Neural architecture search with reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/1611.01578 (2016)."},{"key":"858_CR35","unstructured":"Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. R. Improving neural networks by preventing co-adaptation of feature detectors. Preprint at https:\/\/arxiv.org\/abs\/1207.0580 (2012)."},{"key":"858_CR36","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1007\/s11837-012-0366-5","volume":"64","author":"Y Zhang","year":"2012","unstructured":"Zhang, Y., Yang, X. & Liaw, P. K. Alloy design and properties optimization of high-entropy alloys. JOM 64, 830\u2013838 (2012).","journal-title":"JOM"},{"key":"858_CR37","doi-asserted-by":"publisher","unstructured":"Madsen, J. & Susi, T. The abTEM code: transmission electron microscopy from first principles [version 2; peer review: 2 approved]. Open Res. Eur. https:\/\/doi.org\/10.12688\/openreseurope.13015.2 (2021).","DOI":"10.12688\/openreseurope.13015.2"},{"key":"858_CR38","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1017\/S1431927621000477","volume":"27","author":"BH Savitzky","year":"2021","unstructured":"Savitzky, B. H. et al. py4DSTEM: a software package for four-dimensional scanning transmission electron microscopy data analysis. Microsc. Microanal. 27, 712\u2013743 (2021).","journal-title":"Microsc. Microanal."},{"key":"858_CR39","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42415-y","volume":"14","author":"B Peng","year":"2023","unstructured":"Peng, B. et al. Machine learning-enabled constrained multi-objective design of architected materials. Nat. Commun. 14, 6630 (2023).","journal-title":"Nat. Commun."},{"key":"858_CR40","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.biomaterials.2016.01.012","volume":"83","author":"X Wang","year":"2016","unstructured":"Wang, X. et al. Topological design and additive manufacturing of porous metals for bone scaffolds and orthopaedic implants: a review. Biomaterials 83, 127\u2013141 (2016).","journal-title":"Biomaterials"},{"key":"858_CR41","doi-asserted-by":"publisher","first-page":"184415","DOI":"10.1103\/PhysRevB.92.184415","volume":"92","author":"D K\u00f6dderitzsch","year":"2015","unstructured":"K\u00f6dderitzsch, D., Chadova, K. & Ebert, H. Linear response Kubo\u2013Bastin formalism with application to the anomalous and spin Hall effects: a first-principles approach. Phys. Rev. B 92, 184415 (2015).","journal-title":"Phys. Rev. B"},{"key":"858_CR42","doi-asserted-by":"publisher","first-page":"096501","DOI":"10.1088\/0034-4885\/74\/9\/096501","volume":"74","author":"H Ebert","year":"2011","unstructured":"Ebert, H., K\u00f6dderitzsch, D. & Min\u00e1r, J. Calculating condensed matter properties using the KKR-Green\u2019s function method\u2014recent developments and applications. Rep. Prog. Phys. 74, 096501 (2011).","journal-title":"Rep. Prog. Phys."},{"key":"858_CR43","doi-asserted-by":"publisher","first-page":"3260","DOI":"10.1103\/PhysRevB.31.3260","volume":"31","author":"WH Butler","year":"1985","unstructured":"Butler, W. H. Theory of electronic transport in random alloys: Korringa\u2013Kohn\u2013Rostoker coherent-potential approximation. Phys. Rev. B 31, 3260\u20133277 (1985).","journal-title":"Phys. Rev. B"},{"key":"858_CR44","doi-asserted-by":"publisher","first-page":"13257","DOI":"10.3390\/ijms241713257","volume":"24","author":"T Kosugi","year":"2023","unstructured":"Kosugi, T. & Ohue, M. Design of cyclic peptides targeting protein\u2013protein interactions using AlphaFold. Int. J. Mol. Sci. 24, 13257 (2023).","journal-title":"Int. J. Mol. Sci."},{"key":"858_CR45","doi-asserted-by":"publisher","unstructured":"Peng, B., Heisenberg, D., Cytwyatt & Tung, P.-Y. B. Bop2000\/DANTE: code and data for DANTE. Zenodo https:\/\/doi.org\/10.5281\/zenodo.16225698 (2025).","DOI":"10.5281\/zenodo.16225698"}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00858-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00858-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00858-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T03:04:14Z","timestamp":1758683054000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00858-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["858"],"URL":"https:\/\/doi.org\/10.1038\/s43588-025-00858-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5434645\/v1","asserted-by":"object"}]},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,25]]},"assertion":[{"value":"11 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}