报告时间：8月18日15:00-17：00

报告地点：滴水湖国际软件学院502

报告名称一：Non-convex optimization approach to maximum hands-off control （Prof. Masaaki Nagahara, Hiroshima University, Japan ）

报告摘要:

This talk presents a novel computational method for sparse control, also known as maximum hands-off control, using non-convex penalty functions such as the minimax concave penalty. The sparse control is formulated as the L0-optimal control problem, which is difficult to directly solve. Conventionally, the L1-norm has been used as a surrogate for the L0 norm to numerically obtain the solution. However, the L1-norm approximation may not always yield sparse control. To overcome this difficulty, we propose non-convex functions such as the minimax concave penalty as a surrogate for the L0 norm. We establish the equivalence of the original and proposed control problems without relying on the normality assumption, which is typically required when approximating the L0 norm with the L1 norm. A design example is shown to illustrate the effectiveness of the proposed method.

报告人简介:

Masaaki Nagahara received a bachelor's degree in engineering from Kobe University  in 1998 and a master's degree and a Doctoral degree in informatics from Kyoto  University in 2000 and 2003, respectively. He is currently a Full Professor at the  Graduate School of Advanced Science and Engineering, Hiroshima University. He  has been a Visiting Professor at Indian Institute of Technology Bombay since 2017.  His research interests include control theory, machine learning, and sparse modeling.  He received remarkable international awards: Transition to Practice Award in 2012  and George S. Axelby Outstanding Paper Award in 2018 from the IEEE Control  Systems Society. Also, he received many awards from Japanese research societies,  such as SICE Young Authors Award in 1999, SICE Best Paper Award in 2012, SICE  Best Book Authors Awards in 2016 and 2021, SICE Control Division Research Award   (Kimura Award) in 2020, and the Best Tutorial Paper Award from the IEICE Communications Society in 2014. He is a senior member of IEEE, and a member of IEICE, SICE, ISCIE, and RSJ.

报告名称二：First-Order Projected Accelerated Algorithms （Dr. Mengmou Li, Hiroshima University, Japan ）

报告摘要:

In this talk, we propose a systematic approach for constructing first-order projected  algorithms for optimization problems with general set constraints,   building upon their unconstrained counterparts. We show that these projected  algorithms retain the same linear convergence rate bounds,   when the latter are obtained for the unconstrained algorithms via quadratic Lyapunov  functions arising from integral quadratic constraint (IQC) characterizations. The  projected algorithms are constructed by applying a projection in the norm induced by  the Lyapunov matrix, ensuring both constraint satisfaction and optimality at the fixed  point.

报告人简介:

Mengmou Li is currently a Tenure-Track Associate Professor at the Graduate School  of Advanced Science and Engineering, Hiroshima University, Japan.   He received the B.S. degree in Physics from Zhejiang University, China, in 2016, and  the Ph.D. degree in Electrical and Electronic Engineering from The University of  Hong Kong in 2020. He held postdoctoral positions at The Hong Kong University of  Science and Technology, Hong Kong, the Control Group at the University of  Cambridge, UK, and Tokyo Institute of Technology, Japan. He was a Specially  Appointed Assistant Professor at Tokyo Institute of Technology. His research interests  include power systems, optimization, and robust control.