On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit
arxiv(2021)
摘要
In this work, we consider a distributed online convex optimization problem, with time-varying (potentially adversarial) constraints. A set of nodes, jointly aim to minimize a global objective function, which is the sum of local convex functions. The objective and constraint functions are revealed locally to the nodes, at each time, after taking an action. Naturally, the constraints cannot be instantaneously satisfied. Therefore, we reformulate the problem to satisfy these constraints in the long term. To this end, we propose a distributed primal-dual mirror descent-based algorithm, in which the primal and dual updates are carried out locally at all the nodes. This is followed by sharing and mixing of the primal variables by the local nodes via communication with the immediate neighbors. To quantify the performance of the proposed algorithm, we utilize the challenging, but more realistic metrics of dynamic regret and fit. Dynamic regret measures the cumulative loss incurred by the algorithm compared to the best dynamic strategy, while fit measures the long term cumulative constraint violations. Without assuming the restrictive Slater’s conditions, we show that the proposed algorithm achieves sublinear regret and fit under mild, commonly used assumptions.
更多查看译文
关键词
sublinear dynamic regret,convex optimization problem,time-varying constraints,potentially adversarial,global objective function,local convex functions,constraint functions,primal-dual mirror descent-based algorithm,primal updates,dual updates,primal variables,local nodes,dynamic strategy,fit measures,long term cumulative constraint violations,sublinear regret,distributed online convex optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络