Regret and Cumulative Constraint Violation Analysis for Distributed Online Constrained Convex Optimization

• 成果类型: Article
• 署名作者: Yi, Xinlei; Li, Xiuxian; Yang, Tao; Xie, Lihua; Chai, Tianyou; Johansson, Karl Henrik
• 署名单位: Royal Institute of Technology; Tongji University; Tongji University; Northeastern University - China; Nanyang Technological University
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2022.3230766
• 发表日期: 2023
• 页码: 2875-2890
• 关键词: Convex functions; measurement; Heuristic algorithms; Benchmark testing; Time measurement; STANDARDS; Machine Learning; Cumulative constraint violation; distributed optimization; online optimization; regret; time-varying constraints

摘要

This article considers the distributed online convex optimization problem with time-varying constraints over a network of agents. This is a sequential decision making problem with two sequences of arbitrarily varying convex loss and constraint functions. At each round, each agent selects a decision from the decision set, and then only a portion of the loss function and a coordinate block of the constraint function at this round are privately revealed to this agent. The goal of the network is to minimize the network-wide loss accumulated over time. Two distributed online algorithms with full-information and bandit feedback are proposed. Both dynamic and static network regret bounds are analyzed for the proposed algorithms, and network cumulative constraint violation is used to measure constraint violation, which excludes the situation that strictly feasible constraints can compensate the effects of violated constraints. In particular, we show that the proposed algorithms achieve O(T-max{k, 1-k.}) static network regret and O (T1-k/2) network cumulative constraint violation, where T is the time horizon and.k epsilon (0, 1) is a user-defined tradeoff parameter. Moreover, if the loss functions are strongly convex, then the static network regret bound can be reduced to O(T-k). Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results.