Derivative-Free Optimization

Yang Yu is a professor at Nanjing University, specializing in artificial intelligence, machine learning, and optimization. His research focuses on derivative-free optimization, AutoML, and reinforcement learning. Prof. Yu has an extensive publication record in leading journals and conferences, including Artificial Intelligence, IEEE Transactions on Pattern Analysis and Machine Intelligence, ICML, NeurIPS, IJCAI, and AAAI. He is a co-author of the book Evolutionary Learning: Advances in Theories and Algorithms (Springer, 2019). His work has introduced foundational frameworks and algorithms in classification-based optimization, notably Racos and SRacos, and contributed to the development of the optimization toolbox ZOOpt, widely utilized in academic and industrial research.Hong Qian is an associate professor at East China Normal University, with expertise in optimization algorithms, machine learning, and computational intelligence. His research focuses on developing scalable derivative-free optimization techniques for high-dimensional problems with theoretical guarantees, and LLM for optimization. Dr. Qian has published extensively in prominent venues such as ICML, NeurIPS, AAAI, and IEEE Transactions on Evolutionary Computation and has contributed to advancements in sampling-and-classification frameworks and their applications in machine learning and optimization tasks.Yi-Qi Hu is an AI technical expert in Huawei Co. Ltd., with expertise in machine learning, optimization algorithms, and large language model on device. His work focuses on developing machine learning systems utilizing derivative-free optimization techniques. Dr. Hu has published extensively in prominent venues such as AAAI and IJCAI and has contributed to advancements in derivative-free optimization-based AutoML systems.

• Introduction.- Preliminaries.- Framework.- Theoretical Foundation.- Basic Algorithm.- Optimization in Sequential Mode.- Optimization in High-Dimensional Search Space.- Optimization under Noise.- Optimization with Parallel Computing.