报告题目:Selected Current Research Topics in Evolutionary Multiobjective Optimization

报告人:  Dr. Dimo Brockhoff

时间：2014年10月9日13:00点 

地点：信息学院133会议室

报告摘要:
Multiobjective optimization problems occur in several application domains such as engineering design, finance, or optimal control and evolutionary multiobjective optimization (EMO) algorithms are the methods of choice if the problems are handled as a blackbox or when the objective functions are highly non-linear, rugged, noisy, etc.
In this talk, I am going to present three examples of recent and current research areas in the active field of EMO which are highly linked to my own interests. First, I introduce the idea of optimal $\mu$-distributions as the goal in indicator-based EMO and state the most recent advances. Second, I mention some of our work on decomposition-based EMO, a research area that has re-gained recent interest with the appearance of the MOEA/D algorithm. Third, I will outline our recent efforts towards an automated benchmarking suite for comparing multiobjective blackbox algorithms (not necessarily EMO) based on the state-of-the-art benchmarking platform Coco which has been used in the single-objective blackbox optimization benchmarking (BBOB) workshops held at previous ACM-GECCO conferences.
Besides giving a short overview of my own research interests, I will mention---wherever possible---interesting open research questions that may lead to first collaborative projects.

报告人简介:
Dimo Brockhoff received his diploma in computer science from University of Dortmund, Germany in 2005 and his PhD (Dr. sc. ETH) from ETH Zurich, Switzerland in 2009. Afterwards, he held postdoctoral research positions in France at INRIA Saclay Ile-de-France (2009-2010) and at Ecole Polytechnique (2010-2011). Since November 2011, he has been a permanent researcher at INRIA Lille - Nord Europe, France. His research interests are focused on evolutionary multiobjective optimization (EMO), in particular on theoretical aspects of indicator-based search, algorithm design, and the benchmarking of (multiobjective) blackbox algorithms in general.