首页   系科介绍   师资队伍   科研团队   本科生教学   研究生培养   招聘信息   联系我们

Previous Next
 
首页 >> 学术报告

Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization

马世谦教授(香港中文大学)
2015年1月5日(周一)上午10:00-11:00  闵行校区数学系102报告厅
 
青年学术论坛邀请报告

报告简介:
In this talk we study stochastic quasi-Newton methods for nonconvex stochastic optimization, where we assume that only stochastic information of the gradients of the objective function is available via a stochastic first-order oracle (SFO). Firstly, we propose a general framework of stochastic quasi-Newton methods for solving nonconvex stochastic optimization. The proposed framework extends the classic quasi-Newton methods working in deterministic settings to stochastic settings, and we prove its almost sure convergence to stationary points. Secondly, we propose a general framework for a class of randomized stochastic quasi-Newton methods, in which the number of iterations conducted by the algorithm is a random variable. The worst-case SFO-calls complexities of this class of methods are analyzed. Thirdly, we present two specific methods that fall into this framework, namely stochastic damped-BFGS method and stochastic cyclic Barzilai-Borwein method. Finally, we report numerical results to demonstrate the efficiency of the proposed methods.
   
 
 
快捷链接 >>
 
系内资源 >>
 
教学园地 >>
 
  校外链接 >>    上海市核心数学与基础数学重点实验室    华师大-纽大联合数学中心    上海市数学会    中国数学会    美国数学会    欧洲数学会  
         
       Copyright 2012 All rights reserved    Department of Mathematics, East China Normal University    Tel: 86-21-54342609