2022年2月23日下午15:00,我院邀请清华大学邓柯教授做学术报告,报告由学院院长王纯杰老师和统计系副主任杨凯老师共同主持,我院部分老师、全体研究生和本科生共143人参加了本次线上学术报告会,一同聆听了邓柯教授的真知灼见。
报告人简介:邓柯2008年博士毕业于北京大学,同年进入哈佛大学统计系从事研究工作,历任博士后、副研究员。2013年9月加入清华大学任教至今,现为清华大学统计学研究中心长聘副教授、执行主任。主要从事统计学理论和方法的研究,并致力于推动相关研究工作在生物医学、人工智能、人文及工程等领域的应用。2018年受聘“北京智源人工智能研究院”担任人工智能数理基础方向的“智源研究员”。他是国际计算统计学会亚太地区分会理事、中国现场统计研究会计算统计分会理事长、中国青年统计学家协会副会长、中国人工智能学会智慧医疗专业委员会副主任委员,还担任国际统计学杂志Statistica Sinica副主编,以及《数字人文》、《应用概率统计》、《应用数学与力学》等期刊的编委。
报告摘要:Composed of a large number of sub-wavelength unit cells with designable geometries, meta-materials have been widely studied to achieve extraordinary advantageous and unusual optical properties. However, ordinary computer simulator requires a time-consuming fine-tuning to find a proper design of meta-material for a specific optical property, making the design stage a critical bottleneck in large scale applications of meta-materials. This study investigates the meta-material design under the framework of computer experiments, with emphasis on dealing with the challenge of designing numerous unit cells with functional responses simultaneously, which is not common in traditional computer experiments. We formulate the multiple related design targets as a multi-target design problem. Leveraging on the similarity between different designs, we propose an efficient Bayesian optimization strategy with a parsimonious surrogate model and an integrated acquisition function to design multiple unit cells with very few function evaluations. A wide range of simulations confirm the effectiveness and superiority of the proposed approach compared to the naive strategies where the multiple unit cells are dealt with separately or sequentially. Such a rapid design strategy has the potential to greatly promote large scale applications of meta-materials in practice. The developed method also has the potential to be applied to other problems with similar structure.
会议过程中,邓教授以介绍超材料的物理特性为背景,讲解如何用计算机在空间下利用微元思想模拟超材料结构的方法,通过精心设计的折射场使得光照或其他情况下实现特殊的物理特性。邓教授通过数学和统计方法把连续的折射场进行离散化,改造微元使得超材料能在既定的条件下有可观测的变化。该项目的意义和应用场景十分广泛,例如在航空航天场景下,卫星的圆弧形信号接收板可以通过上述手段改进成平板形状,从而可以缩小卫星的体积和重量等重要属性。
会后,同学们踊跃向老师发出提问,邓教授就在实际计算中如何把结果优化至全局最优等问题为大家分享了他的见解。最后,王纯洁院长在给大家作了展望和鼓励,与会师生纷纷表示,邓教授观点新颖,见地独特,深入浅出,语言风趣幽默;对老师进行教学,学生进行专业学习具有重要指导意义。
2022年2月23日
数学与统计学院