A STOCHASTIC MOVING BALLS APPROXIMATION METHOD OVER A SMOOTH INEQUALITY CONSTRAINT  

作　　者：Leiwu Zhang 

机构地区：[1]Department of Mathematics,Nanjing University,Nanjing 210023,China

出　　处：《Journal of Computational Mathematics》2020年第3期528-546,共19页计算数学（英文）

摘　　要：We consider the problem of minimizing the average of a large number of smooth component functions over one smooth inequality constraint.We propose and analyze a stochastic Moving Balls Approximation(SMBA)method.Like stochastic gradient(SG)met hods,the SMBA method's iteration cost is independent of the number of component functions and by exploiting the smoothness of the constraint function,our method can be easily implemented.Theoretical and computational properties of SMBA are studied,and convergence results are established.Numerical experiments indicate that our algorithm dramatically outperforms the existing Moving Balls Approximation algorithm(MBA)for the structure of our problem.

关 键 词：Smooth convex constrained minimization.Large scale problem.Moving Balls Approximation Regularized logistic regression 

分 类 号：O24[理学—计算数学]