报告人：杨磊副教授

报告题目：Bregman Proximal Point Algorithm Revisited: A New Inexact Version and its Inertial Variant (Authors: Lei Yang and Kim-Chuan Toh)

报告摘要：In this talk, we focus on a general convex optimization problem, which covers various classic problems in different areas and particularly includes many optimal transport related problems arising in recent years. To solve this problem, we revisit the classic Bregman proximal point algorithm (BPPA) and introduce a new inexact stopping condition for solving the subproblems, which can circumvent the underlying feasibility difficulty often appearing in existing inexact conditions when the problem has a complex feasible set. Our inexact condition also covers several existing inexact conditions as special cases and hence makes our inexact BPPA (iBPPA) more flexible to fit different scenarios in practice. As an application to the standard optimal transport (OT) problem, our iBPPA with the entropic proximal term can bypass some numerical instability issues that usually plague the popular Sinkhorn's algorithm in the OT community. The iteration complexity of $O(1/k)$ and the convergence of the sequence are also established for our iBPPA under some mild conditions. Moreover, inspired by Nesterov's acceleration technique, we develop an inertial variant of our iBPPA, denoted by V-iBPPA, and establish the iteration complexity of $O(1/k^{\lambda})$, where $\lambda\geq1$ is a quadrangle scaling exponent of the kernel function. In particular, when the proximal parameter is a constant and the kernel function is strongly convex with Lipschitz continuous gradient (hence $\lambda=2$), our V-iBPPA achieves a faster rate of $O(1/k^2)$ just as existing accelerated inexact proximal point algorithms. Some preliminary numerical experiments for solving the standard OT problem are conducted to show the convergence behaviors of our iBPPA and V-iBPPA under different inexactness settings. The experiments also empirically verify the potential of our V-iBPPA for improving the convergence speed.

报告时间：2023年6月30日，上午10:00-12:00

报告形式：腾讯会议；会议号：358216193

获取会议密码请联系：lixue11240720@163.com

报告人简介：杨磊，副教授、硕士生导师，2022年8月入选中山大学“百人计划”，加入计算机学院科学计算研究所。杨磊博士主要从事最优化理论、算法及其应用研究，目前已在SIOPT, MOR, JMLR, SIIMS, TSP等国际重要期刊上发表多篇论文，主持广东省自然科学基金面上项目1项