报告题目1：Seeking Multiple Solutions: Multi-Modal Optimization using Niching Methods
报告题目2：Decomposition and Cooperative Coevolution Techniques for Large Scale Global Optimization
报 告 人：Xiaodong Li
报告时间1：2018年3月27日（星期二）上午9:00-11:00
报告时间2：2018年3月28日（星期三）上午9:00-11:00
报告地点：老校部二楼大会议室
邀 请 人：工业与系统工程研究所 唐立新教授
Abstract 1: Numerous techniques have been developed in the past for locating multiple optima (global and/or local). These techniques are commonly referred to as "niching" methods, e.g., crowding, fitness sharing, derating, restricted tournament selection, clearing, speciation, etc. In more recent times, niching methods have also been developed for meta-heuristic algorithms such as Particle Swarm Optimization (PSO) and Differential Evolution (DE). In this talk I will introduce niching methods, including its historical background, the motivation of employing niching in EAs, and the challenges in applying it to solving real-world problems. I will describe a few classic niching methods, such as the fitness sharing and crowding, as well as niching methods developed using new meta-heuristics such as PSO and DE. Niching methods can be applied for effective handling of a wide range of problems including static and dynamic optimization, multiobjective optimization, clustering, feature selection, and machine learning. I will provide several such examples of solving real-world multimodal optimization problems.
Abstract 2: Many real-world optimization problems involve a large number of decision variables. For example, in shape optimization a large number of shape design variables are often used to represent complex shapes, such as turbine blades, aircraft wings, and heat exchangers. However, existing optimization methods are ill-equipped in dealing with this sort of large scale global optimization (LSGO) problems. A natural approach to tackle LSGO problems is to adopt a divide-and-conquer strategy. In this talk I will provide an overview on the recent development of CC algorithms for LSGO problems, in particular those extended from the original Potter and De Jong’s CC model. In recent years, several interesting decomposition methods (or variable grouping methods) have been proposed. This talk will briefly survey these methods, and identify their strengths and weakness. The talk will also describe a contribution-based method for better allocating computation among the subcomponents. Finally I will present a newly designed variable grouping method, namely differential grouping, which outperforms those early surveyed decomposition methods.
Resume：Xiaodong Li received his B.Sc. degree from Xidian University, Xi'an, China, and Ph.D. degree in information science from University of Otago, Dunedin, New Zealand, respectively. He is a full professor at the School of Science (Computer Science and Software Engineering), RMIT University, Melbourne, Australia. His research interests include evolutionary computation, neural networks, machine learning, complex systems, multiobjective optimization, multimodal optimization (niching), and swarm intelligence. He serves as an Associate Editor of the IEEE Transactions on Evolutionary Computation, Swarm Intelligence (Springer), and International Journal of Swarm Intelligence Research. He is a founding member of IEEE CIS Task Force on Swarm Intelligence, a Vice-chair of IEEE CIS Task Force of Multi-Modal Optimization, and a former Chair of IEEE CIS Task Force on Large Scale Global Optimization. He was the General Chair of SEAL'08, a Program Co-Chair AI'09, a Program Co-Chair for IEEE CEC’2012, a General Chair for ACALCI’2017 and AI’17. He is the recipient of 2013 ACMSIGEVO Impact Award and 2017 IEEE CIS “IEEE Transactions on Evolutionary Computation Outstanding Paper Award”.
