Problem
Research questions and friction points this paper is trying to address.
decentralized
online optimization
upper-linearizable payoffs
separation access
submodular maximization
Dec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization under Separation Access with Application to Continuous Submodular Maximization
🤖 AI Summary
研究了在分离访问下的分散在线上界线性化优化问题，提出Dec-BFTRL算法，实现每个代理的预期网络总悔恨为约O(√T)。
📝 Abstract
We study decentralized online optimization of upper-linearizable payoffs over an action set under efficient separation access, with applications to online continuous diminishing-return (DR) submodular maximization. We propose Decentralized Barrier Follow-the-Regularized-Leader (Dec-BFTRL), and evaluate each agent's played action against the average of all local objectives. Each agent maps an internal iterate to a feasible action through an approximate gauge projection, communicates only a cumulative surrogate-gradient dual state, and invokes the local HybridNewton procedure to approximately minimize its post-communication BFTRL potential. For every agent, we achieve expected network-aggregate regret of $\widetilde O(\sqrt{T})$. Over $T$ rounds, each agent uses $T$ neighbor-mixing steps and $\widetilde O(T)$ separation-oracle calls. We give four wrapper instantiations covering three DR-submodular maximization problems.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Decentralized Online Optimization
Upper-Linearizable Payoffs
Dec-BFTRL
Approximate Gauge Projection
HybridNewton
🔎 Similar Papers
No similar papers found.
