A Distributed Primal-Dual Algorithm for Bandit Online Convex Optimization with Time-Varying Coupled Inequality Constraints

2020 ◽  
Author(s):  
Xinlei Yi ◽  
Xiuxian Li ◽  
Tao Yang ◽  
Lihua Xie ◽  
Tianyou Chai ◽  
...  
Keyword(s):  
Convex Optimization ◽  
Inequality Constraints ◽  
Time Varying ◽  
Dual Algorithm ◽  
Primal Dual ◽  
Online Convex Optimization

scholarly journals Online Primal-Dual Methods With Measurement Feedback for Time-Varying Convex Optimization

2019 ◽  
Vol 67 (8) ◽  
pp. 1978-1991 ◽  
Author(s):  
Andrey Bernstein ◽  
Emiliano Dall'Anese ◽  
Andrea Simonetto
Keyword(s):  
Convex Optimization ◽  
Time Varying ◽  
Dual Methods ◽  
Measurement Feedback ◽  
Primal Dual

scholarly journals An Implementable First-Order Primal-Dual Algorithm for Structured Convex Optimization

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Feng Ma ◽  
Mingfang Ni ◽  
Lei Zhu ◽  
Zhanke Yu
Keyword(s):  
Convex Optimization ◽  
Practical Interest ◽  
Principal Component ◽  
Objective Functions ◽  
Dual Algorithm ◽  
Proximal Point ◽  
Pursuit Problem ◽  
First Order ◽  
Structured Convex Optimization ◽  
Primal Dual

Many application problems of practical interest can be posed as structured convex optimization models. In this paper, we study a new first-order primaldual algorithm. The method can be easily implementable, provided that the resolvent operators of the component objective functions are simple to evaluate. We show that the proposed method can be interpreted as a proximal point algorithm with a customized metric proximal parameter. Convergence property is established under the analytic contraction framework. Finally, we verify the efficiency of the algorithm by solving the stable principal component pursuit problem.

Sign in / Sign up

Export Citation Format

Share Document