math.OCAug 31, 2026

Dec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization under Separation Access with Application to Continuous Submodular Maximization

Authors: Yiyang LuMohammad PedramfarVaneet Aggarwal

Organizations: Purdue University, West Lafayette, IN, USA · Mila - Quebec AI Institute/McGill University, Montreal, QC, Canada

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 O~(T)\widetilde O(\sqrt{T}). Over TT rounds, each agent uses TT neighbor-mixing steps and O~(T)\widetilde O(T) separation-oracle calls. We give four wrapper instantiations covering three DR-submodular maximization problems.

Explore similar work

CardsList