报告题目：Fast algorithms for solving Stackelberg prediction game with least squares loss

报告人：郦旭东 研究员

单位：复旦大学

时间：2022年12月7日10:00

地点：腾讯会议150-190-907

摘要：The Stackelberg prediction game (SPG) is popular in characterizing strategic interactions between a learner and an attacker. As an important special case, the SPG with least squares loss (SPG-LS) has recently received much research attention. In this talk, we will discuss several efficient algorithms for solving SPG-LS.

简介：郦旭东，复旦大学大数据学院青年研究员。他关注数据驱动大规模优化问题理论、算法及应用。他于2019年获得Mathematical Optimization Society青年学者奖，于2022年获得ICML杰出论文奖，现为Mathematical Programming Computation副主编。

报告题目：A restricted memory quasi-Newton bundle method for nonsmooth optimization on Riemannian manifolds

报告人：唐春明 教授

单位：广西大学

时间：2022年12月8日10:00

地点：腾讯718-950-304

摘要：In this talk, a restricted memory quasi-Newton bundle method for minimizing a locally Lipschitz function over a Riemannian manifold is proposed, which extends the classical ones in Euclidean space to the manifold setting. The potential second order information of the objective function is approximated by applying the Riemannian versions of the quasi-Newton updating formulas. The subgradient aggregation technique is used to avoid solving the time-consuming quadratic programming subproblem when calculating the candidate descent direction. Moreover, a new Riemannian line search procedure is proposed to generate the stepsizes. Global convergence of the proposed method is established: if the serious iteration steps are finite, then the last serious iteration is stationary; otherwise every accumulation point of the serious iteration sequence is stationary. Finally, some preliminary numerical results show that the proposed method is promising.

简介:唐春明，广西大学数学与信息科学学院教授，博士，博士生导师，广西运筹学会副理事长，中国运筹学会理事，广西数学会常务理事。1998-2004年本、硕就读于广西大学，2008年博士毕业于上海大学，2014年到澳大利亚新南威尔士大学访学一年。目前主要研究非光滑优化算法。主持国家自然科学基金项目4项，广西自然科学基金项目3项（含广西杰青1项）。作为主要参与者获广西自然科学奖二等奖2项。在《European Journal of Operational Research》《Journal of Optimization Theory and Applications》《Computational Optimization and Applications》《Optimization Letters》《Optimization》《Numerical Algorithms》《IEEE Transactions on Power Systems》《中国科学：数学》等重要刊物发表论文40余篇。

报告题目：Adaptive scaling damped BFGS method without gradient Lipschitz continuity

报告人：袁功林 教授

单位：广西大学

时间：2022年12月8日8:00

地点：腾讯718-950-304

摘要：The Broyden–Fletcher–Goldfarb–Shanno (BFGS) method plays an important role among the quasi-Newton algorithms for nonconvex and unconstrained optimization problems. However, in the proof of global convergence, BFGS-type methods generally need to assume that the gradient of the objective function is Lipschitz continuous. This issue prompts us to try to find quasi-Newton method for gradient non-Lipschitz continuous and nonconvex optimization based on the classical BFGS formula. In this paper, we propose an adaptive scaling damped BFGS method for gradient non-Lipschitz continuous and nonconvex problems. With Armijo or Weak Wolfe–Powell (WWP) line search, global convergence can be obtained. Under suitable conditions the convergence rate is superlinear with WWP-type line search. Applications of the given algorithms include the tested optimization problems, which turn out the proposed method is powerful and promising.

简介:广西大学数学与信息科学学院教授，博导，副经理，广西应用数学中心常务副主任，国家一流专业（数学与应用数学）负责人；主要研究优化理论与方法及其应用，主持国家基金2项、广西杰出青年基金1项、广西自然科学重点基金1项、中央主导地方科技发展基金1项、广西科技基地和人才专项基金1项、广西面上项目1项；宝钢教育奖，广西“十百千”第二层次人选，广西特聘青年专家；以第一或通讯作者发表SCI论文60余篇，如COAP、JOTA、JCAM等优化和计算期刊、“热点”2篇、“高被引”6篇、出版学术专著2部；获得广西自然科学奖二等奖2项；中国数学会理事、中国数学规划分会理事、广西数学会常务理事、广西运筹学会副理事长。