{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T02:50:19Z","timestamp":1785552619726,"version":"3.56.0"},"reference-count":46,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376109"],"award-info":[{"award-number":["62376109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["62376109"],"award-info":[{"award-number":["62376109"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012216","name":"Jiangsu University of Science and Technology","doi-asserted-by":"crossref","award":["X2026102890014"],"award-info":[{"award-number":["X2026102890014"]}],"id":[{"id":"10.13039\/501100012216","id-type":"DOI","asserted-by":"crossref"}]},{"award":["X2026102890014"],"award-info":[{"award-number":["X2026102890014"]}],"id":[{"id":"https:\/\/ror.org\/00tyjp878","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Given the growing complexity of continuous optimization problems in strongly coupled and black-box environments, this study proposes a novel adaptive gradient-guided metaheuristic, referred to as Self-Adaptive AdamW-Guided Optimization (SAWG). Without requiring explicit gradient information, SAWG constructs population-based pseudo-gradients and systematically integrates key AdamW mechanisms, including adaptive moment estimation, step-size regulation, and weight decay, to guide efficient population updates. Furthermore, a stagnation-aware adaptive control strategy is introduced to alleviate premature convergence and dynamically balance exploration and exploitation. To evaluate the optimization performance of SAWG, experiments were conducted on the CEC2017 and CEC2020 benchmark suites and eight engineering optimization problems. SAWG was also compared with nine other typical and novel high-performance optimizers. Experimental results and statistical analysis show that SAWG achieved excellent optimization performance in most test tasks and maintained strong adaptability and competitiveness in various numerical optimization problems. Therefore, SAWG can be regarded as a high-performance optimizer, providing a novel and effective method for solving complex numerical optimization tasks.<\/jats:p>","DOI":"10.3390\/e28060660","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:50:58Z","timestamp":1781157058000},"page":"660","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-Adaptive AdamW-Guided Optimization: A Learning-Driven Metaheuristic for Solving Complex Real-World Engineering Problems"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7792-1142","authenticated-orcid":false,"given":"Yuhang","family":"Xie","sequence":"first","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Power Engineering, PLA Army Engineering University, Nanjing 210007, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juanjuan","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"ref_1","first-page":"38485","article-title":"Constrained Efficient Global Optimization of Expensive Black-box Functions","volume":"Volume 202","author":"Krause","year":"2023","journal-title":"Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA, 23\u201329 July 2023"},{"key":"ref_2","first-page":"1","article-title":"Learning to Optimize: A Primer and A Benchmark","volume":"23","author":"Chen","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wu, F., Zhang, J., Li, S., Lv, D., and Li, M. (2022). An Enhanced Differential Evolution Algorithm with Bernstein Operator and Refracted Oppositional-Mutual Learning Strategy. Entropy, 24.","DOI":"10.3390\/e24091205"},{"key":"ref_4","first-page":"174","article-title":"Evolutionary Large-Scale Multi-Objective Optimization: A Survey","volume":"54","author":"Tian","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TEVC.2024.3352450","article-title":"Speeding-Up Evolutionary Algorithms to Solve Black-Box Optimization Problems","volume":"29","author":"Echevarrieta","year":"2025","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1109\/TEVC.2023.3250350","article-title":"A Survey on Learnable Evolutionary Algorithms for Scalable Multiobjective Optimization","volume":"27","author":"Liu","year":"2023","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_7","first-page":"1","article-title":"Zeroth-order Stochastic Approximation Algorithms for DR-submodular Optimization","volume":"25","author":"Lian","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/4235.585893","article-title":"No free lunch theorems for optimization","volume":"1","author":"Wolpert","year":"1997","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Nadimi-Shahraki, M.H., Fatahi, A., Zamani, H., Mirjalili, S., and Abualigah, L. (2021). An Improved Moth-Flame Optimization Algorithm with Adaptation Mechanism to Solve Numerical and Mechanical Engineering Problems. Entropy, 23.","DOI":"10.3390\/e23121637"},{"key":"ref_10","unstructured":"Kim, G.Y., and Oh, M.H. (2025, January 24\u201328). ADAM Optimization with Adaptive Batch Selection. Proceedings of the Thirteenth International Conference on Learning Representations, Singapore."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kang, H., Bei, F., Shen, Y., Sun, X., and Chen, Q. (2021). A Diversity Model Based on Dimension Entropy and Its Application to Swarm Intelligence Algorithm. Entropy, 23.","DOI":"10.3390\/e23040397"},{"key":"ref_12","unstructured":"Elkind, E. (2023). Multi-objective Optimization-based Selection for Quality-Diversity by Non-surrounded-dominated Sorting. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, International Joint Conferences on Artificial Intelligence Organization."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101466","DOI":"10.1016\/j.swevo.2023.101466","article-title":"Large-scale evolutionary optimization: A review and comparative study","volume":"85","author":"Liu","year":"2024","journal-title":"Swarm Evol. Comput."},{"key":"ref_14","first-page":"10072","article-title":"Boosting Offline Optimizers with Surrogate Sensitivity","volume":"Volume 235","author":"Salakhutdinov","year":"2024","journal-title":"Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria, 21\u201327 July 2024"},{"key":"ref_15","first-page":"23191","article-title":"Why Do We Need Weight Decay in Modern Deep Learning?","volume":"Volume 37","author":"Globerson","year":"2024","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Doerr, B., and Zheng, W. (2021, January 10\u201314). Theoretical analyses of multi-objective evolutionary algorithms on multi-modal objectives: (Hot-off-the-press track at GECCO 2021). Proceedings of the Genetic and Evolutionary Computation Conference Companion, Virtual.","DOI":"10.1145\/3449726.3462719"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100874","DOI":"10.1016\/j.swevo.2021.100874","article-title":"An Adaptive Iterated Greedy algorithm for distributed mixed no-idle permutation flowshop scheduling problems","volume":"63","author":"Li","year":"2021","journal-title":"Swarm Evol. Comput."},{"key":"ref_18","unstructured":"Yue, P., Yang, X., Xiao, M., and Lin, Z. (2025, January 2\u20137). PseuZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural Networks. Proceedings of the Thirty-Ninth Annual Conference on Neural Information Processing Systems, San Diego, CA, USA."},{"key":"ref_19","first-page":"18374","article-title":"Learning Surrogates for Offline Black-Box Optimization via Gradient Matching","volume":"Volume 235","author":"Salakhutdinov","year":"2024","journal-title":"Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria, 21\u201327 July 2024"},{"key":"ref_20","unstructured":"Loshchilov, I., and Hutter, F. (2019, January 6\u20139). Decoupled Weight Decay Regularization. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"6486","DOI":"10.1109\/TPAMI.2024.3382294","article-title":"Towards Understanding Convergence and Generalization of AdamW","volume":"46","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1109\/TEVC.2021.3130835","article-title":"A Review of Population-Based Metaheuristics for Large-Scale Black-Box Global Optimization-Part II","volume":"26","author":"Omidvar","year":"2021","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_23","first-page":"1","article-title":"Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning","volume":"25","author":"Neumann","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref_24","unstructured":"Elkind, E. (2023). Bayesian Optimization with Switching Cost: Regret Analysis and Lookahead Variants. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, International Joint Conferences on Artificial Intelligence Organization."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Shen, Y., Cai, W., Kang, H., Sun, X., Chen, Q., and Zhang, H. (2021). A Particle Swarm Algorithm Based on a Multi-Stage Search Strategy. Entropy, 23.","DOI":"10.3390\/e23091200"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/TEVC.2022.3155533","article-title":"A Survey on Evolutionary Constrained Multi-objective Optimization","volume":"27","author":"Liang","year":"2022","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_27","unstructured":"Kwok, J. (2025). Reinforced In-Context Black-Box Optimization. Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25, International Joint Conferences on Artificial Intelligence Organization."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.ins.2020.06.037","article-title":"Gradient-based optimizer: A new metaheuristic optimization algorithm","volume":"540","author":"Ahmadianfar","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_29","first-page":"22418","article-title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","volume":"Volume 37","author":"Globerson","year":"2024","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liaw, R.T., and Ting, C.K. (2017, January 5\u20138). Evolutionary many-tasking based on biocoenosis through symbiosis: A framework and benchmark problems. Proceedings of the 2017 IEEE Congress on Evolutionary Computation (CEC), San Sebasti\u00e1n, Spain.","DOI":"10.1109\/CEC.2017.7969579"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Mohamed, A.W., Hadi, A.A., Mohamed, A.K., and Awad, N.H. (2020, January 19\u201324). Evaluating the Performance of Adaptive GainingSharing Knowledge Based Algorithm on CEC 2020 Benchmark Problems. Proceedings of the 2020 IEEE Congress on Evolutionary Computation (CEC), Glasgow, UK.","DOI":"10.1109\/CEC48606.2020.9185901"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"101865","DOI":"10.1016\/j.swevo.2025.101865","article-title":"Neuro-PSO algorithm for large-scale dynamic optimization","volume":"94","author":"Radwan","year":"2025","journal-title":"Swarm Evol. Comput."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.advengsoft.2013.12.007","article-title":"Grey Wolf Optimizer","volume":"69","author":"Mirjalili","year":"2014","journal-title":"Adv. Eng. Softw."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.advengsoft.2016.01.008","article-title":"The Whale Optimization Algorithm","volume":"95","author":"Mirjalili","year":"2016","journal-title":"Adv. Eng. Softw."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1016\/j.future.2019.02.028","article-title":"Harris hawks optimization: Algorithm and applications","volume":"97","author":"Heidari","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/s10462-025-11118-9","article-title":"Tornado optimizer with Coriolis force: A novel bio-inspired meta-heuristic algorithm for solving engineering problems","volume":"58","author":"Braik","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"120069","DOI":"10.1016\/j.eswa.2023.120069","article-title":"Snow ablation optimizer: A novel metaheuristic technique for numerical optimization and engineering design","volume":"225","author":"Deng","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.neucom.2023.02.010","article-title":"RIME: A physics-based optimization","volume":"532","author":"Su","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"113548","DOI":"10.1016\/j.knosys.2025.113548","article-title":"Phototropic growth algorithm: A novel metaheuristic inspired from phototropic growth of plants","volume":"322","author":"Bohat","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_40","first-page":"200558","article-title":"A novel binary Stellar Oscillation Optimizer for feature selection optimization problems","volume":"27","author":"Rodan","year":"2025","journal-title":"Intell. Syst. Appl."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"6476","DOI":"10.1109\/TCYB.2020.3036100","article-title":"Adaptive Control of Subpopulations in Evolutionary Dynamic Optimization","volume":"52","author":"Yazdani","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Xie, Y., Li, W., Qin, B., and Gao, S. (2026). An Enhanced Plant Growth Algorithm with Adam Learning, Levy Flight, and Dynamic Stage Control. Symmetry, 18.","DOI":"10.3390\/sym18010064"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"105521","DOI":"10.1016\/j.engappai.2022.105521","article-title":"A qualitative systematic review of metaheuristics applied to tension\/compression spring design problem: Current situation, recommendations, and research direction","volume":"118","author":"Tzanetos","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_44","first-page":"1039","article-title":"A Comparative Study of Metaheuristic Optimization Algorithms for Solving Real-World Engineering Design Problems","volume":"139","author":"Altay","year":"2024","journal-title":"Comput. Model. Eng. Sci."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"123501","DOI":"10.1115\/1.4068662","article-title":"Multi-Objective Optimization and Supervised Machine Learning for Synthesis of Rolling Element Bearing and Lubricant Selection","volume":"147","author":"Abbas","year":"2025","journal-title":"J. Mech. Des."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"117718","DOI":"10.1016\/j.cma.2024.117718","article-title":"Dream Optimization Algorithm (DOA): A novel metaheuristic optimization algorithm inspired by human dreams and its applications to real-world engineering problems","volume":"436","author":"Lang","year":"2025","journal-title":"Comput. Methods Appl. Mech. Eng."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/6\/660\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:23:53Z","timestamp":1781324633000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/6\/660"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":46,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["e28060660"],"URL":"https:\/\/doi.org\/10.3390\/e28060660","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]}}}