Distributed algorithms for convex problems with linear coupling constraints

被引:0
作者
Colombo, Tommaso [1 ]
Sagratella, Simone [1 ]
机构
[1] Sapienza Univ Rome, Dept Comp Control & Management Engn Antonio Ruber, Rome, Italy
关键词
Nonlinear optimization; Parallel algorithms; Distributed algorithms; Lagrangian methods; DECOMPOSITION ALGORITHM; NONLINEAR OPTIMIZATION; PROBLEMS SUBJECT; CONVERGENCE; DUALITY;
D O I
10.1007/s10898-019-00792-z
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
Distributed and parallel algorithms have been frequently investigated in the recent years, in particular in applications like machine learning. Nonetheless, only a small subclass of the optimization algorithms in the literature can be easily distributed, for the presence, e.g., of coupling constraints that make all the variables dependent from each other with respect to the feasible set. Augmented Lagrangian methods are among the most used techniques to get rid of the coupling constraints issue, namely by moving such constraints to the objective function in a structured, well-studied manner. Unfortunately, standard augmented Lagrangian methods need the solution of a nested problem by needing to (at least inexactly) solve a subproblem at each iteration, therefore leading to potential inefficiency of the algorithm. To fill this gap, we propose an augmented Lagrangian method to solve convex problems with linear coupling constraints that can be distributed and requires a single gradient projection step at every iteration. We give a formal convergence proof to at least epsilon-approximate solutions of the problem and a detailed analysis of how the parameters of the algorithm influence the value of the approximating parameter epsilon. Furthermore, we introduce a distributed version of the algorithm allowing to partition the data and perform the distribution of the computation in a parallel fashion.
引用
收藏
页码:53 / 73
页数:21
相关论文
共 40 条
[1]  
[Anonymous], 2016, IEEE T SIGNAL PROCES
[2]  
[Anonymous], FOUND TRENDS MACH LE
[3]  
[Anonymous], 2010, P SIAMINT C DATAMINI
[4]  
[Anonymous], 2016, IEEE T SIGNAL PROCES
[5]  
[Anonymous], ARXIV180805933
[6]  
[Anonymous], PRACTICAL AUGMENTED
[7]   Sufficient conditions to compute any solution of a quasivariational inequality via a variational inequality [J].
Aussel, Didier ;
Sagratella, Simone .
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2017, 85 (01) :3-18
[8]  
Bertsekas D., 2015, Convex Optimization Algorithms
[9]  
Bertsekas D. P., 1999, NONLINEAR PROGRAMMIN
[10]  
Bertsekas Dimitri P., 1989, PARALLEL DISTRIBUTED