讲座题目：Stochastic alternating structure-adapted proximal gradient descent method with variance reduction for nonconvexnonsmoothoptimization
讲座时间：2023年12月7日星期四15:30-16:30
讲座地点：犀浦校区30456
主讲人简介：张文星，电子科技大学数学科学学院副教授，2012年于南京大学获得博士学位，2014-2015年在法国图卢兹第三大学从事博士后研究。主要研究兴趣为变分不等式算法设计及应用。主持国家自然科学基金面上、青年项目。在MathComput, Inverse Problems, J SciComput,ComputOptimAppl, SIAM J Imaging Sci, IEEE系列杂志发表论文多篇。
讲座内容简介:窗体顶端
The blocky optimization has gained a significant amount of attention in far-reaching practical applications. Following the recent work (M.Nikolovaand P. Tan, SIAM JOptim, 29:2053-2078) on solving a class of nonconvexnonsmoothoptimization, we develop a stochastic alternating structure-adapted proximal (s-ASAP) gradient descent method for solvingblocky optimization problems. By deploying some state-of-the-art variance reduced gradient estimators (rather than full gradient) in stochastic optimization, the s-ASAP method is applicable to nonconvex optimization whose objective is the sum of anonsmoothdata-fitting term and a finite number of differentiable functions. The sublinear convergence rate of s-ASAP is built upon the proximal point algorithmic framework, whilst the linear convergence rate of s-ASAP is achieved under the error bound condition. Furthermore, the convergence of the sequence produced by s-ASAP is established under the K—L property. Preliminary numerical simulations on some image processing applications demonstrate the compelling performance of the proposed method.窗体底端
主办：研究生院 承办：数学学院
